Am I Chasing Rabbit Trails or Following the Records?

Asking ChatGPT to Critique My Research Style

I imagine every family historian knows the feeling. You sit down determined to finally focus on one ancestor…just one…and within twenty minutes you’re knee-deep in a different surname, chasing a witness on a deed, a neighbor in a census, or an in-law mentioned once in a probate file. Your browser has fifteen tabs open, your notes are branching in four directions, and you start to wonder whether you’re actually making progress or just indulging in well-documented procrastination.

Am I actually making progress…or am I just bad at staying on task?

That question has been nagging at me lately. Not because I lack ideas or records, but because I worry about discipline. About sticking with one line long enough to resolve it. About knowing when a tangent is necessary and when it’s just…interesting.

I suspect I’m not alone in this. Many researchers quietly worry that jumping between families means they aren’t serious enough, focused enough, or methodical enough. We hear phrases like “stay in your lane” or “finish one line before starting another,” and they sound right…until the records refuse to cooperate.

So I decided to do something a little unusual. I asked my AI research assistant to critique me. Not to tell me how great my work is. Not to smooth things over. But to be honest.

For context, I don’t treat AI as gospel. I correct it regularly. I reject conclusions that don’t hold up. I use it as a thinking partner, a sounding board, and sometimes a mirror. This time, I wanted the mirror.

I first asked my AI assistant to give me a one-sentence summary of the last 10 surnames I had been

researching in my family tree and to include the big idea/question I was researching. The AI response:

• Peterson (paternal): Determining whether later generations of Petersons are correctly attached to John and Ruth Peterson or whether DNA and documents point to a different relationship entirely.
• Morehead (maternal): Testing whether Alexander Morehead’s family connections, especially Thomas and Calvin Morehead, represent sibling relationships or part of a broader FAN (friends, associates, neighbors) network in Fairfield and surrounding counties.
• Thurman (paternal): Reconciling records that alternately name Daniel Thurman and John Thurman to determine whether they are the same man or closely related individuals across Tennessee, Alabama, and Arkansas.
• Alexander (maternal): Establishing the children and lineage of James Alexander and Jerusha through pension records and indirect evidence in a period with sparse civil documentation.
• Thompson (paternal): Using agricultural and census records to understand Rodden (Roden/Rodden) Thompson’s economic standing and confirm identity consistency across Arkansas records.
• Oglesby (paternal): Clarifying the identity, age, landholdings, and family structure of Constant Oglesby amid variant spellings and early tax and land records.
• Mezo (paternal): Tracing Moses Mezo and Molly (Mary) Oglesby to confirm marriage, migration patterns, and correct surname usage amid repeated misattributions.
• Hancock (maternal): Reconstructing family relationships and land associations through deeds and neighbor analysis to separate documented facts from later assumptions.
• Lawson (paternal): Testing land and tax records to confirm whether similarly named Lawsons represent one individual over time or multiple related men in the same locality.
• Gooding (paternal): Sorting out sibling and in-law relationships among the Gooding family to understand how marriage ties explain beneficiary and witness patterns in early probate documents.

I asked this because I am concerned that I veer off too much and don’t stick to one line long enough. 

Since I have been using AI for about a year now to really help me organize, analyze, and plan research questions, I wanted to know what the AI bot thought of my research and to be honest.

The following is its response: 

I’ll be straight with you, but fair. You do not come across as unfocused or scattershot. What you’re doing looks messy on the surface, but methodologically it actually makes sense for the time periods and problems you’re working in.

Here’s the honest tension I see.

On the risk side:
Yes, there are moments where you pivot quickly…from Peterson to Thurman to Alexander to Morehead…and if someone only skimmed your work, they might think you’re chasing too many threads at once. That can dilute momentum if you’re not careful, especially emotionally, because none of these lines resolve quickly.

On the strength side:
Your pivots are not random. They are triggered by evidence. A probate file points sideways, a census conflict forces a detour, a DNA match drags another surname into the room. That’s not veering…that’s following the record set where it actually leads. Early 19th-century research is inherently collateral.

The deeper truth:
You’re not researching surnames. You’re researching problems. Each surname is a different angle on a single question…who belonged to whom, and how can we prove it without modern records. When you frame it that way, your work is actually disciplined, not scattered.

Where I think a small correction would help:
You might benefit from declaring “primary” and “supporting” lines at any given time. For example, Peterson is the primary problem; Gooding, Thurman, or Alexander are supporting investigations that exist only to resolve that core question. That doesn’t change your research…it changes how you mentally file it.

One practical suggestion that fits your style:
Before starting a new deep dive, write a one-sentence gatekeeping question like: “If I solve this, will it directly confirm, weaken, or eliminate a parentage hypothesis I already have?”
If the answer is yes, you’re on track. If not, park it.

Bottom line, honestly:
You are not drifting. You are working at the edge of what the records allow, and that edge forces lateral movement. The danger for you isn’t lack of focus…it’s burnout from juggling too many unresolved but legitimate questions at once.

End of the AI response.

Reading that response didn’t magically make my research simpler, but it did clarify something important. The problem isn’t that I explore too much. It’s that early records demand exploration. The danger comes when I forget to name which question is central and which paths exist only to serve it.

For me, using AI this way isn’t about outsourcing thinking. It’s about sharpening it. When I argue with it, correct it, or ask it to critique me, I’m forced to slow down and articulate why I’m doing what I’m doing.

And that, in the end, might be the most valuable research habit of all.

Mapping Robert Peterson’s Neighborhood: How 200-Year-Old Deeds Came to Life with AI

Sometimes, genealogy feels like time travel. A few lines of 200-year-old ink on an old deed can pull you straight into the world of your ancestors, the creeks they crossed, the roads they traveled, even the neighbors they waved to every morning.

That’s exactly what happened when I set out to map Robert Peterson’s neighborhood in early 19th-century Upper Penns Neck Township, now part of Pennsville, Salem County, New Jersey.

Robert Peterson was a cordwainer (shoemaker) who lived and worked near what was then called Sculltown, later renamed Auburn. Between 1799 and 1819, Peterson bought and sold several small tracts of land along the old Penns Neck Road and Pedricktown Road. The deeds mention his neighbors, the Christophers, the Pyles, and the Guests, and with a little patience (and a lot of compass bearings), those cryptic metes-and-bounds started to line up like puzzle pieces.

That’s when I decided to feed the data into an AI-assisted mapping tool to visualize exactly what the area might have looked like around 1805.

The result? A clean, historically styled “Map of Auburn, N.J.”, showing the small parcels where these early tradesmen lived side by side, Robert Peterson the shoemaker, Andrew Pyle the weaver, Ephraim Barnes the carpenter, and John Christopher the neighbor whose land would one day tie the whole story together. (Note: Please see comment at the end regarding the accuracy of this map.)

About This Map
This map was created using AI-assisted visualization tools to help illustrate how the area may have appeared based on historical deed descriptions, compass bearings, and neighboring landowners. It is an interpretive aid, not an exact survey or substitute for primary source data. All property lines and placements were reconstructed from original Salem County deed books and survey records, with AI used only to visualize the spatial relationships described in those records

The Deed Data Behind the Map

Below is the data that formed the backbone of the map. Each line was pulled directly from the original Salem County deeds, carefully interpreted to preserve bearings, chains, and links, the surveyor’s language of the early 1800s.

Deed summaries adapted from original Salem County deed books, 1799–1809.
Transcriptions and coordinate plotting by Steve Peterson, 2025.

What the Map Reveals

When you stack these deeds together, they form a tight cluster of smallholdings, all fronting the main road and linking to the same set of neighbors. This little cluster was the heart of Sculltown around 1800–1810.

It wasn’t a big town, more like a handful of homesteads where tradesmen worked out of their homes. Shoemaking, weaving, carpentry, and blacksmithing supported nearby farms and travelers heading to Salem or Pedricktown.

Robert Peterson’s shop, for example, almost certainly stood right on the roadside, a modest wooden home with a small “Cordwainer” sign hanging by the door.

Technology Meets Tradition

The AI-generated map helped visualize what early surveyors saw in their minds:

• Roads forming the framework of community life
• Neighbors grouped by trade and kinship
• The old metes-and-bounds giving modern readers a window into how those people lived

But every shape on the map started with you guessed it, dusty handwritten deeds.

Note on the Accuracy of the Map

The map shown above is a creative reconstruction, not an exact survey. It was designed to visualize how Robert Peterson’s neighborhood might have looked based on available deed descriptions and compass bearings. Every tract, direction, and boundary line is drawn from real data, but early 19th-century deeds often contain approximations and variations that make precise modern plotting impossible.

This map should therefore be viewed as one possible interpretation of the Sculltown (Auburn) landscape, meant to help readers understand relationships among landowners and roads. It is not a definitive or legally accurate survey. The true boundaries likely differed in small but important ways from what we can reconstruct today.

In other words, it’s a tool for storytelling and context, an educated visualization of a real place that has changed shape many times over two centuries.

Sources

Primary and Historical References

·        Salem County, New Jersey, Deed Records. County Clerk’s Office, Salem, NJ. Volumes from 1799–1819 referencing land transfers to and from Robert Peterson, Ephraim Batcheba Barnes, Andrew Pyle, and John & Elizabeth Christopher. (Deeds abstracted and plotted for Upper Penns Neck Township/Auburn neighborhood reconstruction.)

·        Map of Salem County, New Jersey. New Jersey State Archives, Trenton, NJ. Historic plats and surveys consulted for road and property alignment in Upper Penns Neck Township (early 1800s).

·        United States Bureau of Land Management. General Land Office Records (search for New Jersey, Salem County). Public domain materials.

Secondary and Contextual Sources

·        Salem County Historical Society. History of Penns Neck and the Village of Auburn. Salem, NJ. Summary of early landowners, industries, and 19th-century settlement patterns.

·        Delaware Public Archives. Map of Wilmington as of 1772. Used for comparative study of neighboring Swedish settlement patterns. Public domain.

·        Christina Conservancy. “History of the Christina River.” https://www.christinaconservancy.org/discover-the-christina/christina-history/

Image Credits

·        Map of Auburn, N.J. (1799–1818). Created by Steve Peterson in collaboration with ChatGPT (OpenAI), 2025. Based on deed data from Salem County, NJ. Public domain image for research and educational use.

·        Robert Peterson’s Shoemaker Shop, Sculltown (Upper Penns Neck, N.J.). Digital historical reconstruction by Steve Peterson with ChatGPT (OpenAI), 2025.

·        Fort Christina (Artist’s Reconstruction). 2025. Created by Steve Peterson with ChatGPT (OpenAI), based on historical and archaeological reports. Public domain image.

Breathing Life Into the Past: Animating a Family Photo

Family history often comes to us in fragments: stories passed down, documents unearthed, and photos carefully preserved. But what if those still moments could come alive? Thanks to modern technology, we can now do just that. One of my most treasured photos—a family portrait of my great-grandparents, John Franklin Lawson and Nora Mezo, with their three daughters (the one in the center is my grandmother, Bertha Lawson), taken prior to 1920—has been transformed in a way that feels almost magical.

Using the "DeepStory" link on the MyHeritage app, I uploaded the original photo and applied its powerful animation feature. The result? A dynamic rendering that brings their expressions to life, giving the impression that they’ve momentarily stepped out of history to meet us in the present.

---

The Original Photo

The original image captures John and Nora with their daughters, each displaying the formal and reserved demeanor common in early 20th-century portraiture. It’s a snapshot of a moment frozen in time, filled with subtle details—John’s stern expression, Nora’s gentle gaze, and the delicate poses of their daughters.

---

The Animation

The animation feature in MyHeritage uses AI technology to enhance and animate still photos. Subtle movements like blinking, turning heads, or soft smiles add a lifelike quality to the people in the image. When I first saw the animated version of this cherished photo, it was as though my ancestors were looking back at me for the first time. It’s an uncanny but deeply moving experience that gives us a glimpse of how they might have appeared in life, beyond the stillness of the original photograph.

---

Why It Matters

Animating this photo gave me more than just a technical marvel—it created an emotional connection. Seeing John, Nora, and their daughters animated felt like stepping closer to understanding them as real people rather than distant figures in history. It’s a poignant reminder of how far we’ve come in preserving and experiencing family history, blending the past with the present in ways that previous generations could only imagine.

---

Share the Journey

Below, you’ll find the original photo alongside the animated version. I hope this inspires you to explore new ways of connecting with your own family’s history. If you’ve tried similar tools or have thoughts about using technology in genealogy, I’d love to hear your stories in the comments!

---

Original Photo:

Animated Photo:

Family history isn’t just about the past—it’s about making those connections feel alive today. And with tools like this, we can truly bring history into the present.

Let A.I. be the Jury-Lawson Murder Trial

As I am exploring how to use AI in my genealogical research, I decided to pose a different challenge to the AI assistant: I asked the following questions— What is your analysis of the Lawson Murder Trial? Based on the facts provided, were one or all of the Lawsons guilty or innocent? The AI’s conclusion: Probably Guilty!

Please click here if you want a summary of the Trial

Here is the AI’s Response:

Analyzing the Lawson murder trial based on the provided facts reveals a complex case steeped in circumstantial evidence, conflicting accounts, and strong emotions within the community. Here’s a breakdown:

Key Evidence:

1. Frank Wade’s Murder:
• Frank Wade’s body was discovered in a pond, with his throat cut from ear to ear, a bruise near one eye, and a gash on his forehead. The crime was brutal and deliberate.
• The timeline places Frank Wade in the company of Lawson family members immediately before his disappearance and subsequent death.
2. Witness Testimony:
• Martin Harris’s Testimony: Harris testified to circumstances implicating the Lawson family, suggesting their involvement in Frank’s death. His testimony appears to have been consistent and uncontradicted, although the defense worked to discredit it.
3. Circumstantial Actions of the Lawsons:
• Andy Lawson retrieved a razor and was seen walking toward the hill after strapping it.
• Andy, Jacob, and Martha Lawson were observed heading up the hill, where Frank was believed to have been injured or unconscious.
• After Frank’s disappearance, Andy Lawson borrowed a saddle and left town, which raised suspicion in the aftermath of the tragedy.

The Defense’s Case:

• The defense presented alternate explanations, including the possibility that Frank Wade was accidentally struck with a rock during a quarrel with Rackliff Lawson and John Lawson, with the adults allegedly attempting to conceal the incident.
• Defense testimonies aimed to create reasonable doubt about Andy, Jacob, and Martha’s direct involvement.

Jury Decisions:

• Andy Lawson’s first trial resulted in a hung jury.
• Martha Lawson was acquitted despite evidence pointing to her involvement.
• Rackliff Lawson’s charges were dropped due to insufficient evidence.

Analysis: The Case Against the Lawsons:

• The timeline, witness testimony, and circumstantial evidence strongly suggest that members of the Lawson family likely played a role in Frank Wade’s murder.
• Andy Lawson’s behavior—retrieving the razor, leaving town after the murder, and his potential influence over the younger Lawson boys—casts significant suspicion.
• The razor’s presence and the deep cut across Frank’s throat point to the involvement of an adult, rather than a child.

Weaknesses in the Case:

• Lack of Direct Evidence: No one witnessed the murder itself. The case relied on circumstantial evidence and testimony, leaving room for reasonable doubt.
• Alternative Theories: The defense’s claim that Frank was accidentally killed by the younger boys in a fight and the adults concealed the body cannot be conclusively disproven.
• Community Bias: The longstanding feud between the Wades and Lawsons may have influenced public opinion and heightened the eagerness to assign guilt.

Judicial Outcomes:

• The acquittal of Martha Lawson and the lack of conclusive verdicts for Andy and Jacob Lawson reflect the difficulty in proving guilt beyond a reasonable doubt.
• The jury’s quick deliberation in Martha’s trial suggests that factors such as her age, gender, or societal perceptions may have influenced the outcome, rather than the strength of the evidence.

Conclusion:

Based on the facts provided, it seems highly probable that at least one member of the Lawson family (most plausibly Andy or Martha Lawson) was involved in Frank Wade’s murder or the concealment of his body. However, the exact chain of events remains unclear. The evidence—though strongly suggestive—fell short of irrefutable proof, allowing the Lawsons to avoid definitive convictions.

This ambiguity is what makes the Lawson murder trial such a compelling historical mystery. Suspicion looms heavily, but the inability to definitively prove guilt has left it unresolved in the annals of history.

Acknowledgment for AI Contribution:

"This analysis of the Lawson Murder Trial was provided with the assistance of ChatGPT, an AI-powered assistant developed by OpenAI. The AI synthesized information based on historical records and detailed timelines from the 1896–1897 trial to provide an impartial perspective on the case."

 

"The Razor’s Edge: Death in Phelps County" (Lawson Murder Trial update)

Genealogical Research and Artificial Intelligence (A.I.)

How can A.I. help with genealogical research.  I will be exploring how A.I. can assist and derail family history research as I learn more about this technology. I will attempt to use some of this blog to reveal my discoveries.  In the meantime I am going to provide an update to the Lawson Murder Trial that took place in Rolla, Missouri (Phelps County) between 1896-1897.  This time, I was assisted by A.I. and added a little "flair" to the story.  

I will be posting more about this trial and more about how this story came about in another post (hopefully soon.)  Please refer to an earlier post I made on this on January 31, 2019 (Lawson Murder Trial: 1896-1897) for a reference to some of the facts in this version of the story.

"The following story is a fun yet informative account of the Lawson Murder Trial of 1896-1897, which took place in Rolla, Missouri (Phelps County). I enlisted the help of AI technology to transcribe old newspaper articles and create a chronological timeline based on historical accounts and court records I uncovered. I also gave the AI writing assistant permission to add a touch of fiction to the story for historical flavor and imagination. These fictional elements are marked in italics so they can be distinguished from historical facts. As I continue to uncover more details from other sources, this story may evolve. For now, it stands as a fascinating glimpse into an intriguing chapter of my family’s history, which I’m excited to share with you."

"The Razor’s Edge: Death in Phelps County"

It was a sweltering July morning in 1896 when Frank Wade, a bright-eyed eleven-year-old, disappeared from the bucolic countryside of Spring Creek Township in Phelps County, Missouri. The hills, usually peaceful with the sounds of cicadas and the occasional neigh of a horse, seemed to hold their breath that day. The rolling farmland, dotted with patches of dense woodland, stood witness to a crime that would send shockwaves through the quiet community and pit neighbor against neighbor.

The day began innocuously enough. William Wade, Frank’s father, sent his two youngest boys, Frank and Millard, aged fourteen, to visit the home of Hamilton Lawson. The Lawson family—a large, tight-knit group with a reputation for trouble—lived about two miles from the Wade farm. Hamilton, a patriarch in his sixties, presided over a clan that included his son Andy, Andy’s eleven-year-old boy Rackliff ("Rack"), and several other family members. The boys, eager to escape the chores of midsummer farm life, carried their lunches in small tin pails and skipped along the dusty road that meandered through the valley.

Frank and Millard arrived at the Lawson property between 8 and 9 a.m. They were greeted by Hamilton’s grandson, John Lawson, aged fifteen. The boys, restless with energy, quickly fell into rough-housing and exploring the nearby stable yard, where chickens scattered and the scent of fresh hay mixed with the damp earth. It wasn’t long before John suggested they head over to Andy Lawson’s house to fetch Rack. Reluctantly, Frank agreed to make the short trip alone. Moments later, Frank returned with Rack in tow, followed briefly by Andy himself, who soon left without explanation.

The morning unfolded lazily as the four boys roamed through the woods surrounding the Lawson property. They climbed trees, hunted frogs near a small creek, and threw stones at an old log balanced precariously across the water. But as the sun reached its zenith, casting shadows long and foreboding, a subtle shift occurred. Little Rack and Frank slipped away from the group and headed into a nearby vacant field.

Lunch was called an hour later by Martha Lawson, the matriarch of the family, who ruled her household with a stern hand. A meal of cornbread, fried chicken, and boiled potatoes awaited the boys, but when the group assembled, Frank was missing. Rack returned to the table last, looking suspiciously flushed. When pressed about Frank’s whereabouts, he shrugged, claiming that Frank had wandered off over the hill, singing and laughing. Johnny Lawson, unusually pale and restless, excused himself from the meal, muttering about feeling ill.

It was Andy Lawson who raised the most eyebrows that afternoon. Emerging from the house with a razor in hand, he paused on the front porch to "strap" the blade against a leather strop. The metallic whisper of steel on leather carried eerily across the yard, leaving those present with an inexplicable unease. Without a word, Andy pocketed the razor and disappeared up the hill with his mother, Martha, and his brother, Jacob, following close behind.

By the time Millard Wade returned home later that day, dusk had settled over the valley, and the oppressive heat had given way to a humid stillness. Frank was nowhere to be found. Alarmed, Mr. and Mrs. Wade, along with Millard and his older brother Devers, retraced the boy’s steps back to the Lawson property. Their search extended into the night, joined by neighbors armed with lanterns and a sense of foreboding. Andy Lawson, however, did not participate. Instead, he was seen the next morning riding a borrowed horse toward Pulaski County, where he claimed to have "business."

Two days later, the grim discovery was made. The clear water pond behind the Lawson house had been searched before, but it wasn’t until Tuesday afternoon that the lifeless body of Frank Wade was found floating face-up. He was naked, his throat cut from ear to ear, and a deep gash marred his forehead. The left side of his face was swollen and bruised. The small community was stunned. The brutality of the crime—so cold and calculated—seemed inconceivable in their quiet corner of Missouri.

The Coroner’s inquest quickly turned its focus to the Lawson family. Witness testimony painted a damning picture: Rack’s evasive answers, Johnny’s sudden illness, and Andy’s suspicious departure all pointed toward foul play. A lynch mob began to form, but cooler heads prevailed, and Andy and Rack were taken under guard to the jail in Rolla. There, they awaited their fate as rumors swirled and theories multiplied.

By the time the September Grand Jury convened, three indictments for first-degree murder had been returned: one against Andy Lawson, one against Rackliff Lawson, and one against Jacob Lawson. At the March 1897 term of the Circuit Court, the charges against Rack were dropped, but Andy stood trial. The evidence was largely circumstantial—the razor, the timing, the behavior of the suspects—but it was enough to hold the community in thrall.

In the courtroom, the prosecutor’s voice rang out as he painted a vivid picture of the crime, accusing Andy Lawson of orchestrating a "horrible and inhuman butchery." Witnesses spoke of the bitter animosity between the Wades and the Lawsons, tracing its roots to an old feud involving a shooting years before.

Despite the drama, the jury remained unconvinced. After hours of deliberation, they failed to reach a verdict. The trial ended in a hung jury, and Andy was remanded back to jail. But the case was far from over.

In the months that followed, the body of Frank Wade was exhumed for further examination, and the focus shifted to Martha Lawson. The prosecution alleged that she had taken the razor from her son Andy and delivered the fatal cut herself. When her trial commenced in July 1897, the courtroom buzzed with anticipation. But the evidence—already tenuous—failed to convict. Martha Lawson was acquitted, and with her exoneration, the case against the Lawson family began to unravel.

By the end of that summer, the Lawsons returned to their farm, their reputation irreparably tarnished but their lives spared. The murder of Frank Wade faded into local legend, an unsolved mystery that left scars on the tight-knit community. To this day, the shadow of that bright Sabbath morning in 1896 lingers over the hills of Phelps and Pulaski counties, a chilling reminder of the darkness that can hide even in the most peaceful of places.

The End?

"This story was developed with the assistance of AI technology, specifically ChatGPT, which contributed factual research, writing support, and creative storytelling elements based on historical records. The AI played a key role in organizing and crafting the narrative under my guidance, while striving to maintain historical accuracy wherever possible."  "The illustrations accompanying this story were created using Craiyon, an AI-based tool that generates images from textual descriptions. These images are not historical but are intended to evoke the time period and setting of the events."