I. Introduction: The Power of A.I. Genealogical Prompt Chaining
Welcome to the fascinating world of AI applications, where the dynamic use of language models continually expands our capabilities and insights. Today, we venture further into this realm to explore an exciting concept: prompt chaining.
Prompt chaining is a powerful tool that taps into the versatility of AI, enabling us to extend the utility of a single interaction by linking it to subsequent prompts. In essence, it is a relay race of information processing where the output of one AI operation serves as the input to another. This chain of operations harnesses the potential of AI to process, generate, and analyze data in a seamless flow, creating opportunities for multi-faceted inquiries and sophisticated data manipulation. Most simply, prompt chaining is using the response from one A.I. interaction as the prompt for a following interaction.
Our exploration of prompt chaining builds upon the foundations we established in previous blog posts. We delved into structured data extraction from narrative sources, shedding light on how we can extract valuable insights from complex texts. In another post, we introduced ChatGPT plugins, an innovative extension of OpenAI’s powerful language model, GPT-4, which further enhances its capabilities.
Today, our journey takes us to a fascinating intersection of these concepts. We aim to illustrate how prompt chaining can be effectively combined with the “Show Me” diagramming plugin for ChatGPT. This plugin translates textual relationships into illustrative diagrams, providing a visual representation of the relationships extracted from narrative sources.
However, a quick but important caveat before we proceed: the advanced features we’ll be discussing, including the “Show Me” plugin, require a subscription to ChatGPT Plus. While the primary value of this subscription lies in gaining access to the latest and most powerful iteration of the language model—GPT-4—the plugins definitely add a delightful layer of functionality, the proverbial icing on the cake.
This post will introduce and develop an understanding of prompt chaining. Building on a general definition and description of prompt chaining, four cases studies will be considered to sharpen our imagination of how prompt chaining will evolve as the number of A.I.-assisted genealogical use cases (tasks) grows.
II. Background Information
The “Show Me” diagramming plugin is an innovative tool integrated with OpenAI’s language model, ChatGPT. It’s designed to help generate visual diagrams based on user inputs. With this plugin, users can request ChatGPT to draw diagrams, flowcharts, or even family trees. Its applications are broad, making it a versatile and practical tool for visual learners, project managers, educators, and in our case, genealogists.
To fully appreciate the potential of the “Show Me” diagramming plugin and how it can be utilized in genealogical research, it’s essential to familiarize oneself with some of our previous posts. These articles delve into the practical applications of AI in genealogy, and specifically, how ChatGPT can be utilized to extract and organize valuable information.
The article “AI and Genealogy: Using ChatGPT to Glean Info from Obits, Articles, and Announcements” provides a comprehensive exploration of how ChatGPT can extract genealogical information from text sources like obituaries, wedding announcements, and newspaper articles. The post demonstrates how the AI can be prompted to identify relationships between individuals, create markdown tables of this information, and even generate GEDCOM files, which can be used to create family trees.
Another key post to review is “Using ChatGPT Plugins for Genealogy“. Leveraging ChatGPT Plus plugins can substantially enhance artificial intelligence-assisted genealogy. These software add-ons customize ChatGPT for genealogical research, with the AskYourPDF plugin as a key example. This tool allows for interaction with PDF files, extracting crucial data from scanned records or historical articles. These plugins automate tasks and interact with digital resources, increasing efficiency and insight in genealogical research, symbolizing the promising future of AI in genealogy. The plugin used extensively in this post, the “Show Me” diagramming plugin, is also introduced in that earlier blog post.
Those two previous posts provide a solid foundation for understanding how AI, and more specifically, ChatGPT with its plugins, can revolutionize genealogical research. As we move forward today, we will explore how the “Show Me” diagramming plugin, in particular, can provide a visual dimension to relationships.
You know the saying, “A picture is worth a thousand words.” That saying is never more true than in genealogy–relationships are hard for others to understand when presented only as a stream of names. Seeing a diagram of the relationships among people–a family tree or a pedigree chart–is a tremendous aid to understanding. Visually presenting relationships helps us communicate our research and findings in a way that others are more easily able to understand. The “Show Me” plugin empowers genealogists to use A.I. to generate charts, diagrams, and family trees from textual, natural language descriptions.
The advent of A.I. plugins, however, in early summer 2023 is just developing from infancy to early childhood. My research and experience during this season is that many plugins have great potential, but currently exhibit significant shortcomings. Specifically, the “Show Me” plugin demonstrated extensively in this post would currently received a grade of “C-” but with the expectation that this will, for reasons I will explain below, improve soon to a useful “B+”.
Finally, before we jump into the case studies, a brief preview and explanation. The last two case studies involve research as genealogists might typically conduct: the consideration of an earlier researcher’s work and the examination of an obituary. The first two case studies, however, use as their subject matter fictional places and people. This was done for several reasons. First, readers are likely to be familiar with one or both of the peoples and places in these first two case studies. Second, the people and relationships offered by these fictional examples are extensive, allowing for a better presentation of the principles being demonstrated. And finally, third, well, it was fun. I pray these first two fictional examples won’t distract any readers so much as to inhibit their ability to see the underlaying processes at work. That said, let’s jump into the case studies.
III. Case Study 1: Complex Family in “One Hundred Years of Solitude”
“One Hundred Years of Solitude,” a widely acclaimed novel by Gabriel García Márquez, offers a fascinating exploration of the Buendía family over seven generations in the fictional town of Macondo. The intricate relationships and complex family dynamics in this novel make it an ideal case study for demonstrating the capabilities of ChatGPT and the “Show Me” diagramming plugin in handling complex genealogical data.
To begin, we would need to extract the relationship information from the text. This process involves identifying and understanding the connections between the various characters in the novel. With the assistance of ChatGPT, this is made significantly easier. By providing the AI with a well-crafted prompt, we can instruct it to sift through the text and identify the relationships between characters, as well as the events that bind them together.
For example, a prompt may be constructed as follows:
PROMPT: Assume the role of an expert, professional genealogist. Consider the genealogically relevant information that might appear in the novel "One Hundred Years of Solitude". I would like to know about the stated relationships between characters in the text. When you can with certainty, state the relationship between two characters in the book. Extract names and relationships from "One Hundred Years of Solitude" and present that information in a way that the next AI, a diagram-generating AI, can use your information, in turn, to create a family relationship visualization.
ChatGPT, with its impressive language processing capabilities, then extracts the relationship information and organize it. [NOTE: In this example, I did not feed the entire novel to ChatGPT to process. In all the following examples and case studies, however, the A.I. is restricted to using only information that I provide to it.]
The response did not look enough like a prompt for the next AI, so I prompted ChatGPT to refine its response. As we have noted before, just as “writing means re-writing,” so working with A.I. is often an iterative, refining process; that is, we don’t often get things perfect on the first attempt, so try, try again, until you get what you need.
The refinement looked like a great prompt for the “Show Me” plugin. So, once we have this relational data, we can use it to create a prompt for the “Show Me” plugin to generate a visual representation of the Buendía family tree. The next prompt, then, could look something like this, which is just an exact copy-and-paste from the last response:
"SHOW ME" PROMPT: Show me a family tree for the Buendía family from "One Hundred Years of Solitude" by Gabriel Garcia Marquez using the following relationships:
1. José Arcadio Buendía is married to Úrsula Iguarán. They have two children: Aureliano Buendía and José Arcadio.
2. Aureliano Buendía is married to Remedios Moscote. They have a daughter named Renata Remedios, also known as Meme.
3. José Arcadio is married to Rebeca. They have a son named Arcadio.
4. Arcadio is married to Santa Sofía de la Piedad. They have three children: Remedios the Beauty, Aureliano Segundo, and José Arcadio Segundo.
5. Aureliano Segundo is married to Fernanda del Carpio. They have three children: Renata Remedios (also known as Meme), José Arcadio (II), and Aureliano (II).
6. Meme is married to Mauricio Babilonia. They have a daughter named Renata Remedios, also known as Renata.
7. José Arcadio (II) is married to Renata. They have a son named Aureliano (III).
Please note that there are multiple characters named Aureliano and José Arcadio in the family, so make sure to differentiate between them in the family tree.
The result would be a detailed diagram illustrating the family relationships of the Buendía family. This visual representation, built on the foundation of meticulous data extraction and AI processing, allows us to easily understand and analyze the complex familial dynamics present in “One Hundred Years of Solitude”.
Sharp-eyed readers will here observe why I currently graded the “Show Me” plugin as a “C-“. Notice that spouses are not placed on the same row or level as their partners, but instead are one level below with the children. There are work-arounds and solutions to this problem (some easy, as noted below), but users should be aware of this issue in the spring/summer of 2023. Both the “Show Me” plugin and the other diagramming plugins available in the ChatGPT plugin store rely on a graphic tool called “Mermaid“; Mermaid is great for many, many uses, but it is, obviously, not created primarily to generate family trees. The developers of Mermaid, though, are working to explicitly add family tree diagrams to the tool’s repertoire. As I mentioned, though, there are work-arounds currently available, and every diagram that is generated is easily editable with a link that is included with every chart.
So, that shortcoming acknowledged, do not let the perfect be the enemy of the good. What ChatGPT and the “Show Me” plugin did, even though not perfect, is still fairly amazing. In about three-and-a-half minutes, the genealogically relevant information was extracted from a 440 page novel and transformed into a family tree. The implications of this process are significant. Not only does it provide a visual aid for understanding complex relationships in literature, but it also has the potential to be a valuable tool in fields such as education, history, and of course, genealogy. By making it easier to visualize and comprehend complex familial relationships, the “Show Me” plugin enhances our ability to extract deeper meanings and insights from texts. Moreover, it demonstrates the potential for AI to transform how we approach, engage, and understand large bodies of text.
IV. Case Study 2: Tolkien’s Universe
The second case study, as I mentioned, also draws from the world of relationships in literature. I’m no Tolkien-head, so it was a bit unusual for a “Lord of the Rings” post to appear in my social feed. I’ve enjoyed the movies and read a couple of the books, and I know just enough to have heard that Tolkien is often credited with developing a literary universe. So when glanced at the article in my feed, I quickly noticed that it would lend itself nicely to this demonstration of chain prompting data extraction and data visualization. Tolkien’s universe offers a compelling backdrop against which we can further demonstrate the potential of prompt chaining with ChatGPT and the “Show Me” diagramming plugin.
The article I stumbled across was rich in relationships between people and, well, something else. So, whether you’re navigating the familial ties of the House of Elrond or tracing the lineage of the Dwarven clans, Tolkien’s works are filled with complex genealogical data that could be readily extracted by an AI. To begin this process, we would again need to construct a suitable prompt that instructs ChatGPT to identify and delineate the relationships between the various characters within Tolkien’s universe.
A sample prompt might look like this:
PROMPT: You are a professor of literature with deep expertise in science fiction and fantasy. Find below an article about Tolkien's "Lord of the Rings" universe. As if you were a genealogist, I want to map, chart, diagram, or in some way visualize the relationships between creatures and characters in the article. Please suggest how that might BEST be done, then attempt to do whatever you can do to visualize the relationships, even if it's not the best possible way imaginable.
Lord of the Rings: What Does Sauron Look Like Under His Armor? It's Complicated
Guided by this prompt, ChatGPT would then delve into the texts and extract the necessary relationship data, organizing it into a structured format for easy interpretation and analysis.
With the relationship data in hand, we can then feed this information into the “Show Me” plugin to generate a diagram that visualizes these connections. This might involve creating a new prompt such as:
"SHOW ME" PROMPT: Show me a diagram of the lineages and relationships in Tolkien's universe using the following relationship data.
I gathered a lot of information on the cosmology and beings of Tolkien's universe, which can serve as a basis for creating a diagram or chart to visualize the relationships between the creatures and characters in the "Lord of the Rings". Here are the main points:
[COMPLETE DESCRIPTION FOLLOWED]...
The result? A comprehensive and easily digestible diagram that visually represents the complex relationships in Tolkien’s universe. This visual aid can be a powerful tool for understanding and exploring the intricacies of Tolkien’s rich lore, making it accessible and engaging for both seasoned fans and newcomers alike. It should not take too much imagination to see how this process is analogous and applicable to genealogy.
Furthermore, this case study underscores the potential of prompt chaining with AI in enhancing our understanding of literature. By enabling us to visualize complex relationships and lineages, the “Show Me” plugin can bring to life the rich tapestry of connections that form the backbone of our favorite family history stories. In this way, we can unlock deeper insights and appreciation for the families that we love, showcasing the immense potential of AI as a tool for genealogical analysis and exploration.
V. Case Study 3: Family Biographical Sketch
As we transition from literature to a genealogical context, let’s move into the realm of family biographical sketches. These sketches are rich sources of family history, often containing detailed information about relationships, life events, and personal narratives that can be invaluable in genealogical research.
In this case study, we’ll explore how a family biographical sketch can provide the data needed for prompt chaining and how this approach can bring the intricate web of familial relationships to life. In this example, it took me about six minutes to take a photo of a book page with my phone, extract the text from the phone, then use ChatGPT 4 to extract the relationship information from the text, and finally have the “Show Me” plugin generate a family tree diagram.
Family biographical sketches typically provide in-depth information about a family, including relationships, dates and locations of important events, occupations, and sometimes even anecdotes that give unique insights into the lives of our ancestors. These sketches, while rich in information, can sometimes be challenging to navigate due to their narrative format and the sheer volume of information they contain.
Here’s where prompt chaining with ChatGPT and the “Show Me” plugin can prove invaluable. By directing ChatGPT to extract the genealogical data from the biographical sketch, we can transform the narrative data into a structured format, ready for visualization.
The initial prompt could be framed like this:
PROMPT: You are an expert genealogist and the world's best prompt engineer. Find below an excerpt from a genealogical text. Your response will be passed to another AI which is capable of creating a diagram of family relationships. Extract information about people and relationships. Interpret that information and use it to craft a prompt for the diagramming AI. Your response should be in the form of a prompt for the other AI.
THE AMBROSE PARKS LITTLE FAMILY
The earliest known ancestor of the numerous Littles in Ashe County is Isaac (ca. 1800-1892).
[BIOGRAPHICAL SKETCH CONTINUES...]
Once the relationships are extracted, the data can be fed into the “Show Me” plugin with a prompt like this:
"SHOW ME" PROMPT: Based on the provided genealogical text below, show me a diagram representing the reported relationships. Combine Husbands/Wives into one node; for example "Isaac Little married Elizabeth Poe" is one node, and the parents together of their children.
1. The earliest known ancestor is Isaac Little (ca. 1800-1892), who married Elizabeth Poe, daughter of Mathias and Sarah (Grimsley) Poe. Isaac and Elizabeth had thirteen children, including Ambrose Parks Little.
[GENEALOGY CONTINUES AS SHOWN ABOVE...]
The resulting diagram brings clarity to the complex relationships described in the biographical sketch. This visual representation of family connections can be an invaluable tool for genealogists, making it easier to understand and trace familial relationships across generations. Note the instruction in bold in the prompt; this is the work-around to get the “Show Me” plugin to place mothers and fathers on the same row, line, or level in a family tree diagram; for now, they need to be treated as one unit, that is, as the parents together. Again, this deficiency will be addressed and remedied in time. Advanced users may want to note that the Mermaid scripting language is easily accessible and configurable for every diagram that the “Show Me” diagram generates.
Furthermore, it highlights the power of prompt chaining in a genealogical context. By transforming narrative data into structured, visual representations, we can unlock a new dimension of understanding in our family history research. This case study serves to showcase how the combined power of AI and genealogy can enrich our understanding of our past, bringing our ancestors’ stories to life in a compelling and accessible way.
VI. Case Study 4: Obituaries
Continuing in our genealogical context, let’s turn our attention to obituaries, a commonly used but often underappreciated resource in genealogical research. Obituaries are a treasure trove of information, offering insights into the lives of our ancestors, their relationships, and their place in the community.
In this case study, we’ll explore how obituaries can provide valuable data for prompt chaining and how this method can bring new insights to genealogical research.
Obituaries are unique in their ability to encapsulate the essence of a person’s life, including their family ties, accomplishments, and legacies. However, the narrative format and sometimes cryptic language used in obituaries can make extracting this information a challenge. This is where AI, particularly ChatGPT, can step in.
To initiate the process, we would provide ChatGPT with a prompt to extract relevant information from an obituary. The prompt could be framed as:
PROMPT: You are an expert genealogist and the world's best prompt engineer. Find below an excerpt from a genealogical text. Your response will be passed to another AI which is capable of creating a diagram of family relationships. Extract information about people and relationships. Interpret that information use it to craft a prompt for the diagramming AI. Your response should be in the form of a prompt for the other AI.
Mrs. Houck, 53, Buried Saturday
Funeral service was held on Saturday at 11:00 a.m., at the Bethany Church, for Mrs. Annie Houck, 53, of West Jefferson, who died at her home on Thursday, January 20, after being ill for some time. The service was conducted by Rev. R. G. Wagoner and Rev. T. J. Houck, and burial followed at the Bethany Cemetery.
Mrs. Houck, who was a native of Ashe County, the daughter of Jacob Goodman and Sarah Tatum Goodman, is survived by her husband, James Houck, and the following children: Mrs. Dora Howell, Todd; Fay, Agnes and Jessie D. Houck; Phil Houck, of the U.S. Army, stationed in South America, and J. C. Houck, Jr., of the Navy, stationed in Maryland.
The data extracted by ChatGPT can then be used to create a prompt for the “Show Me” plugin to visualize these relationships:
"SHOW ME" PROMPT: Based on the provided genealogical text below, show me a diagram representing the reported relationships. Combine Husbands/Wives into one node; for example "Annie Goodman married James Houck" is one node, and the parents together of their children.
Based on the provided genealogical text, please create a diagram representing the following relationships:
1. Mrs. Annie Houck, born as Annie Goodman, was the daughter of Jacob Goodman and Sarah Tatum Goodman. She was married to James Houck.
2. Annie and James had six children: Mrs. Dora Howell; Fay Houck; Agnes Houck; Jessie D. Houck; Phil Houck, who is in the U.S. Army, stationed in South America; and J. C. Houck, Jr., who is in the Navy, stationed in Maryland.
Please represent these family relationships, including marriages and offspring, in the family diagram.
The resulting diagram provides a visual representation of the relationships gleaned from the obituary, offering a unique perspective on the family structure and relationships of the deceased.
The value of this approach in genealogical research is manifold. Not only does it allow for the efficient extraction of valuable information from obituaries, but it also presents this information in a clear, visual format that can aid in understanding complex family relationships and in tracing lineages. It demonstrates the power of prompt chaining in unlocking the potential of obituaries as a source of genealogical data, bringing us one step closer to the stories of our ancestors.
Looking forward, the potential of prompt chaining is immense. As the capabilities of AI tools like ChatGPT continue to expand, the possibilities for prompt chaining grow exponentially. The fine-tuning of the diagrams provided by the “Show Me” plugin, for instance, could lead to more nuanced and detailed visualizations of data, further enhancing our understanding of complex information.
Every week, we witness the introduction of new use cases – data extraction, translation, optical character recognition (OCR), narration, and diagramming, among others. With each new task that AI can handle, the potential combinations of prompt chaining multiply dramatically, broadening the horizons of AI-assisted endeavors, such as genealogy. This continuous growth in AI capabilities underscores the increasing relevance and power of prompt chaining.
In the present, we manually chain or link prompts, carefully curating the sequence to accomplish our specific goals. Yet, we can envision a future, perhaps not too distant, where AI agents will not only suggest optimal task combinations but also carry out complex workflows seamlessly, further reducing the manual effort and increasing the efficiency of achieving more intricate goals.
I invite all readers to dive into this fascinating world of AI-assisted research. Try out the “Show Me” plugin and experiment with prompt chaining. The journey may challenge your understanding of what AI can do and inspire you to imagine new ways to harness its power.
We would love to hear about your experiences, discoveries, and insights in this area. Please share your results in the Comments section below. Remember, every experiment, every question, every insight adds to our collective understanding of this powerful tool.
Here’s to the continued exploration of AI’s potential, and to the remarkable power of prompt chaining!