More in Family history.
Match census tick marks to family names with ChatGPT
WorkedEvidence: Screenshots or logsPosted Last checked
ChatGPT matched 1790 and 1800 census tick marks to the Reed family's children for a genealogy blogger in a few prompts.
How to use this
- Tap Copy prompt.
- Open ChatGPT.
- Paste it into the message box.
- Send it, then read the answer before acting on it.
New to this? What's a prompt?
A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.
Prompt
Recreated prompt
The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.
The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.
Here is a census entry for Benjamin Reed's household with the tick marks by age group, and the list of children with birth years from a published family history. Work out each child's age at the census, which column each one fits, and show where the counts match and where they don't, in a table.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Compare a census entry's age-group tick marks with a family list, and show where they match and where they don't. Questions to ask me first: - Which census year and place, and what are the age columns? - Where does the family list come from, and are birth years exact or estimated? - Do you have the census image or only a transcription? Inputs (fill in or confirm): - Census image or transcription: [UPLOAD IMAGE] - Census year and age columns: [YEAR / COLUMNS] - Family list with birth years: [LIST AND SOURCE] Rules: - Read the counts from the census exactly as recorded; if the image is unclear, say which marks you can't read. - Work out each person's age on the census date and show the math. - Show matches and mismatches in a table, and don't explain away a mismatch. - Say clearly that this supports or doesn't support the family list; it doesn't prove it. Checkpoint: Show me the counts you read from the census before comparing, so I can check them against the image. If you get stuck: If a birth year is missing, list the possible age groups instead of guessing one. Verify before you finish: Recheck every age calculation and column total. Output: A table of names, ages and columns, then a short note on matches and gaps. Done when: I can see which family members fit the census and which don't.
AI tool
Outcome
A genealogy blogger named Diana used ChatGPT to compare early census tick marks with a published family history that lists ten children for Benjamin Reed and Huldah Pratt of Woodford, Vermont. Early censuses only count people by age group, so the job is working out which child fits each mark. ChatGPT calculated each child's age group and built comparison tables. The 1790 census didn't fully match: four sons were expected under sixteen, but the census counted three. By 1800 the household of nine lined up very neatly with the younger children. Diana reviewed the comparison and conclusions, and noted that AI did not prove the genealogy correct, but what usually takes well over an hour took only a few prompts.
Evidence: Screenshots or logsThe source shows screenshots, a transcript or the AI's output.
Source
- Posted
- by Diana (Moments in Time, A Genealogy Blog)
- Last checked
- Method:
- How we verify
https://momentsintimeagenealogyblog.blogspot.com/2026/06/using-ai-to-give-names-to-tick-marks.html
Context: The 1790 census counted one fewer son than expected; the blogger checked the original census image.
More in Family history
Find leads on an 1800s Edinburgh ancestor's parents with ChatGPT
ChatGPT gave Janice Wellard new places to search for an ancestor's parents, but it read burgess roll dates wrong and repeated itself.
PartialChatGPTEvidence: Described by posterView CaseTranslate old Norwegian and German records with Gemini, Claude and ChatGPT
Gemini did the best job translating Kitty Cooper's old records, but Claude gave a partial and ChatGPT made stuff up.
PartialGemini +2Evidence: Screenshots or logsView CaseCatch a wrong birthplace in a family tree with a NotebookLM Audio Overview
A NotebookLM Audio Overview made a genealogist notice that an ancestor's recorded birthplace didn't match the records.
WorkedNotebookLMEvidence: Described by posterBeginner-friendlyView CaseSearch 40+ sources on a brick wall ancestor's FAN Club with NotebookLM
NotebookLM searched 40+ sources at once with citations and helped Lisa Rex confirm a migration pattern from Ohio to Illinois.
WorkedNotebookLMEvidence: Described by posterBeginner-friendlyView CaseTranscribe an 1829 handwritten deed with Claude and check it against a manual copy
Claude 3.5 Sonnet transcribed an 1829 deed almost perfectly for genealogist Nicole Dyer, but misread the key surname Peerson.
WorkedClaudeEvidence: Screenshots or logsBeginner-friendlyView CaseCompare four AIs transcribing a 1700s will found with FamilySearch full-text search
Dana Leeds tested Copilot, Gemini, ChatGPT and Claude on a 1700s will. Claude was most accurate, but each made spelling mistakes.
PartialClaude +3Evidence: Screenshots or logsView Case
Similar cases
Break a six-year family history brick wall with help from ChatGPT
ChatGPT couldn't answer outright, but it spotted patterns and a wrong lead that helped two cousins end a six-year search.
WorkedChatGPTEvidence: Described by posterView CaseSeparate land descriptions in an 1836 dower record with ChatGPT
ChatGPT separated a 113-acre tract from a 43¾-acre dower in an 1836 record and linked the widow to a figure in medical history.
WorkedChatGPTEvidence: Described by posterView CaseTrace a family tree from half-remembered details with ChatGPT (partial)
From vague details, ChatGPT found a grandfather's obituary and a possible Virginia line, but the other side stalled in West Virginia.
PartialChatGPTEvidence: Described by posterView CaseTranscribe and date 150 old family letters for an archive with ChatGPT
A genealogy volunteer used ChatGPT to transcribe about 150 letters from 1885 to 1925, then date them from clues in the text.
WorkedChatGPTEvidence: Described by posterView Case

