5 Ways to Use ChatGPT to Research an Ancestor

Blog post - 5 Ways to Use ChatGPT to Research an Ancestor

You may have been wondering how ChatGPT can help with genealogical research. This is a first look at using ChatGPT for research about a specific ancestor. For simplicity our conversation focused on where to find information, rather than on more complicated topics. ChatGPT held its own in our conversation, and was a pleasant companion and offered answers based on its training.

You can view our other posts about Artificial Intelligence, Artificial Intelligence and Genealogy and Getting Started with ChatGPT for when you are ready to try it!

NOTE: DO NOT ENTER PRIVATE OR SENSITIVE DATA INTO ChatGPT. Your data is used for training, and is reviewed by OpenAI to verify that content complies with their policies and safety requirements. They may be used for training purposes.

1. Ask ChatGPT general questions. Unless your ancestor is notable or famous, your main benefit will come from looking for general information about individuals with similar origins, living conditions or professions.

In my ongoing research into using ChatGPT for genealogical research, I decided to focus on one ancestor who has been a brick wall.

I started by asking if ChatGPT knew my ancestor. I did not expect an answer for an ancestor who was not a public figure, but I thought I would ask.

I'm sorry, but I don't have any information

2. Forming questions/prompts is an important part of getting the most out of conversations with ChatGPT. Sometimes you need to rephrase or reformulate your approach to obtaining information.

I thought that ChatGPT might have more general information about immigrants from County Sligo, Ireland, so I asked a more general question::

What can you tell me about immigrants from Sligo, Ireland to the United States?

ChatGPT answered with general information about Sligo immigrants, sharing their reasons for emigrating and where they tended to settle in the United States, and which popular professions they chose.

3. ChatGPT cannot footnote its answers. It can give sources that were used to build its knowledge base.

When I asked what sources ChatGPT what sources it used for the answer about Sligo. Since it is a trained artificial intelligence, and not a lookup service, this is like asking a person on the street to cite the sources for the statements they make in conversation.

What sources did you use for the above answer?

In response, I reformulated my question:

What sources do you recommend for researching an ancestor from Sligo?

ChatGPT offered five suggestions. This was more successful, until it was not. The suggestions were solid, but the details behind them were sometimes general and may not be up-to-date. (Remember, ChatGPT knows nothing of the world since 2021 and is NOT connected to the Internet.) The description it offered for civil registration records did not include the fact that many can be found online for free. The census records advice was factual about when censuses were conducted, but did not relate that only fragments exist for other than 1901 and 1911.

  1. Civil registration records
  2. Church records
  3. Census records
  4. Local history resources
  5. DNA testing

4. Given a list of facts, ChatGPT can write a smooth narrative.

Next, I entered a text version of a timeline for Timothy Gilroy’s life. The text was copied then pasted into the prompt.

Below is a timeline of events

ChatGPT interpreted the data correctly, and fed back a narrative incorporating the facts. This was how I gave ChatGPT the data for my next questions.

Thank you for timeline

5. ChatGPT can make good research suggestions. Treat ChatGPT’s research suggestions as hints. Be ready to investigate the leads it gives, keeping in mind that it may not know every aspect of every record set.

Remember that you are having a conversation with ChatGPT, and it remembers previous input in the same chat.

Next I asked: Can you suggest genealogical research ideas for Timothy Gilroy

ChatGPT pleasantly answered with a list of ideas. (Details of each item are omitted for brevity.)

  1. Research his family in Sligo County, Ireland
  2. Find records of his immigration
  3. Locate records of his military service
  4. Explore his occupation
  5. Investigate his naturalization record
  6. Look for church records
  7. Conduct DNA testing
These are just a few ideas

Since these were just “some” ideas, I asked: Do you have additional ideas?

ChatGPT was more than willing.

  1. Explore the neighborhood where he lived
  2. Investigate the history of Irish immigrants in Newport
  3. Search for newspaper articles
  4. Consult with local historical societies or genealogical societies
  5. Utilize online genealogical resources

ChatGPT is ready and willing to help us research our ancestors. We have to be clear in our conversations, and be ready to ask questions from different perspectives. Overall, the ideas ChatGPT offered were sound. Of course, they were general and did not have all the potential constraints. ChatGPT stressed learning about context in many of the research questions, which was good. Of course, be sure to use its suggestions as just that, and not definitive facts.

The above conversation was with ChatGPT Mar 23 Version. Free Research Preview.

Getting Started with ChatGPT

Blog post banner - Getting Started with ChatGPT

By now you have probably heard about OpenAI’s systen, ChatGPT. You can use the Preview Preview for free with an account. ChatGPT has a number of ways it can support the genealogical community, covered in Artificial Intelligence and Genealogy. It can also support your personal genealogical efforts, covered in other posts.

NOTE: DO NOT ENTER PRIVATE OR SENSITIVE DATA INTO ChatGPT. Your data is used for training, and is reviewed by OpenAI to verify that content complies with their policies and safety requirements. They may be used for training purposes.

Once you establish an account, using ChatGPT is as easy as typing in your questions or requests, which become the “prompts” to which ChatGPT generates responses. Underneath the hood, ChatGPT uses prompt engineering as part of its natural language processing capabilities to get meaningful responses from its models. Knowledge databases, texts, and other sources as well as an understanding of language has been used to train its neural network. When it has not been trained about a specific topic, it uses relevant information from external sources. ChatGPT answered a few questions about this for me. ChatGPT told me it did not search the web as humans would. In fact, ChatGPT is not connected to the Internet, and it has limited knowledge of world events after 2021. In response to another question, ChatGPT answered that it did not need question marks for it to understand that I asked a question, but that using them might clarify the input.

You can use the research preview of ChatGPT for free. You own the output that is created. The output from a paid or free plan can be reprinted, sold and merchandised.

To get a free research account https://chat.openai.com/and select “Sign up” and follow the steps.

Welcome to ChatGPT

To sign up for an account, you have to provide your email address and a phone number. The email address and phone number do have to be validated before your account is activated.


The “Send a message…” box at the bottom is where to type a question or issue a request.

At the end of the generated response, you can continue the conversation by asking another question. You also have the option to select “Regenerate response” to make ChatGPT process the request again and generate another response.

Regenerate response button

NOTE: If you choose to REGENERATE RESPONSE, the original one will be replaced. So, if you are looking to combine or compare responses, be sure to copy the original response.

Your conversations will appear on the left side of the screen in a laptop or desktop browser. You have the option to edit the automatically assigned label for the chat, or delete it. There is also an option to begin a “New chat.” NOTE: Conversations with the Free Research Preview are reviewed to improve systems and to verify that content complies with their policies and safety requirements. They may be used for training purposes. You can request to delete your conversations from a link in the FAQ.

New chat, chat label

Here is an example where I started out with a simple question in my message prompt: What is a GEDCOM file?

ChatGPT example

ChatGPT answered this prompt. While it was answering, there was an option to “Stop generating” the response. Note the “Regeneration response” button at the bottom of the reply.

Example conversation

In the image above, you can see the thumbs up and down buttons so that you can provide feedback by about the answers.

The same prompts generated different responses, as evidenced by the regenerated responses. To see if the responses might be presented in a preplanned sequence, I asked a friend to enter the same prompt (different than the example given). The response she received certainly had similar elements, but the responses were definitely not the same. The responses were more different than rearranged words; the concepts were expressed in a different manner.

The conversations you have with ChatGPT can be saved through browser addons, but I found it far simpler to copy-and-paste into Word or Wordpad documents (for now).

As for how long my input prompt could be, I asked ChatGPT directly about that. The answer is 2048 tokens, which can be interpreted as characters. ChatGPT needs you to know that a spaces and punctuation marks count.

Input question

This technology really is impressive. I began with giving specific prompts but before too long I found myself falling into a pattern like conversation with the ChatAPT. It seemed very natural. I could also ask for clarification about a previous answer, or change the intent of my question. I could lead the conversation in different directions based on the responses. According to the ChatGPT FAQ, https://help.openai.com/en/articles/6783457-chatgpt-general-faq

ChatGPT Mar 14 Version of the Free Research Preview was used for examples in this tutorial. Future releases may have slightly different interfaces and options.

Artificial Intelligence and Genealogy

By now, you have probably heard about ChatGPT. This blog post will discuss how Artificial Intelligence (AI) is used in Genealogy with the help of ChatGPT.

In other posts I will cover how to use ChatGPT and some other AI tools that can help you in the pursuit of genealogy.

Genealogy is the study of family history and ancestry, and it has become increasingly popular in recent years. With the advancement of technology, researchers have been able to access more information about their ancestors, making the process of genealogy more accessible and convenient. Artificial intelligence (AI) has played a significant role in making genealogy research more efficient and effective.

AI is a technology that uses algorithms to mimic the human brain’s decision-making process. When it comes to genealogy, AI can be used to sift through large amounts of data, uncovering hidden connections, and providing insights that would have been difficult to find otherwise.

Here are some of the ways AI is being used in genealogy research:

  1. Record Linkage: Record linkage is a process that involves connecting different sources of data to create a comprehensive profile of an individual. AI algorithms can match and link various documents such as birth certificates, marriage licenses, and census data, making it easier to trace family lineage.
  2. Facial Recognition: Facial recognition technology can analyze photos and match them with other images in the database, creating a visual family tree. It can also be used to identify unknown ancestors in old family photos.
  3. DNA Analysis: AI can analyze DNA test results to find genetic matches and identify relationships between family members. It can help to identify distant cousins, uncover ethnic origins, and find long-lost family members.
  4. Translation: AI-powered translation tools can help researchers decipher and translate foreign language documents, which can be a valuable resource for uncovering family history in different parts of the world.
  5. Predictive Analysis: AI can analyze existing data to create predictive models of likely family connections. This can help researchers to identify family members they might not have known existed and to predict possible future discoveries.

In conclusion, AI has revolutionized the field of genealogy by enabling researchers to access and analyze vast amounts of data quickly and accurately. By using AI-powered tools and techniques, genealogy researchers can unlock a wealth of information about their ancestors and uncover hidden connections that would have been impossible to find otherwise. As the technology continues to evolve, it is likely that genealogy research will become even more accessible and exciting.

Book Review: “Generation by Generation”

Generation by Generation cover

With a wealth of knowledge and experience in researching, lecturing, and teaching others, Drew Smith has now turned his efforts to create a book for those who are beginning their genealogical research in the United States. “Generation by Generation: A Modern Approach to the Basics of Genealogy” is a concise way for new genealogists to benefit from Mr. Smith’s wisdom as well as enjoy his warm and approachable manner. He makes good use of analogies and examples so that the content is manageable by even the most novice researcher.

Part I of the book lays a solid foundation of key knowledge and skills a reader needs to conduct successful genealogical research. In Part II, readers are guided while they actually research their own ancestors. The book lends itself to navigating through its sections in order, supporting the reader with both a table of contents and an index.

The topics covered in Part I are important to understand and practice for successful research outcomes. Given that understanding cousin relationships can be tricky, the book is specific with regard to those relationships. Topics from changing calendars to DNA are presented clearly and painlessly throughout. As I was reviewing this section the book, I found that just as I would wonder, “will he tell beginners about…,” he did! The breadth of those examples ranged from genetic recombination and to ethics of DNA testing to the fact that the records of the Freedmen’s Bureau also include records of employees. The importance of introducing the genealogical research process and the Genealogical Proof Standard (GPS) to new genealogists cannot be overstated. The book conveys an appreciation of citing sources, while eliminating the fear of them.

A key part of researching using “Generation by Generation” is helping a new researcher travel back in time, organizing how they will research within each time frame of generations of ancestors. The book provides descriptions of which records are appropriate for each time frame. With Mr. Smith’s guidance, the researcher steps backwards through their US ancestors’ generations who lived during the time periods: 1950 to now, 1880-1950, 1850-1880, 1776-1850 and pre-1776 British America. Mr. Smith also supports readers as they start to tackle researching their ancestors back to their European or Canadian roots. These divisions are logical, and it would be straightforward to follow the book’s structure to approach personal research or formulate a syllabus for a class or study group.

Another feature is due to the printing process. The chapters that contain an odd number of pages include a blank page at the end. These blank pages are an ideal location to enter notes and record questions.

This is a book to both read and use. It is a way for a reader to bring Mr. Smith home and have him alongside while taking significant steps to research their family history. Using Part I to learn the main ideas and terminology, and pitfalls, prepares the reader to be ready to do their own research using Part II, and have a good foundation before advancing into more detailed research.

The book is available at Genealogical.com and other booksellers.

Notes: A review copy of the book was provided by the publisher. Like many other genealogists, I am a fan of The Genealogy Guys podcast, and recognize both of its hosts for service to the genealogical community.

This blog post is copyright ©2023 by Margaret M. McMahon. All rights reserved. No part of this post may be reproduced in any manner whatsoever without written permission, except in the case of brief quotations in articles and reviews. All copyrights and trademarks mentioned herein are the possession of their respective owners and the author makes no claims of ownership by mention of the products that contain these marks.

Cultural Anthropology and Genealogy

Blog Header Cultural Anthropology and Genealogy

Cultural Anthropology

Last semester I took a third course in anthropology. After taking courses in Archaeology and Biological Anthropology, the next for me to tackle was Cultural Anthropology. (Our local community college does not offer a course in the fourth area of anthropology, linguistic anthropology.) Due to the nature of the subject material, this class was the least rooted in hard science. Cultural Anthropology studies how a society organizes itself. This is done through its beliefs, and how people live, think, create and find meaning. It introduces the concept that cultures have an intrinsic logic in their practices.

A big part of this branch of anthropology is fieldwork. Anthropologists in the field study societies, collecting data to build ethnographies. This data is often qualitative. Originally fieldworkers studied societies as impartial and distant observers; later they shifted to coming off the veranda to be participant observers.

When we go beyond our ancestors’ birth and death dates to fill in the dashes with what they did between those two dates, we are doing something similar to the fieldwork done by anthropologists. We often wish that we could go back in time to come off the veranda to be participant observers but lacking that option we can use the older anthropologists’ method of building their work on others’ first-hand source material. In our pursuit, we can use published sources that were contemporary to their times to learn about their culture at their time. When we research and write about our ancestors, we are building an ethnography. We can interact with the artifacts that they and their contemporaries left behind, which is like the activities of archaeologists.

Even though we cannot be participant observers in our ancestor’s society during their time, sometimes we can participate with a society that is close to theirs. This can be done through participating in ethnic crafts, cooking, dancing, clothing, reading the books they read, learning stories they told and heard, and learning about or practicing their beliefs.