Guido Thys
Vice-President of the Antwerp Bibliophile Society
Amsterdam, The Netherlands
Actions
Guido Thys (b. 1956) studied General, Psycho- and Neurolinguistics and the Philosophy of Language in Antwerp (B), Leuven (B), Brussels (B) and Salzburg (AT). As a Lecturer in Strategy, Marketing and Database Management at a Business School, he (co-)authored 20 books & dozens of articles on these subjects and has presented over 2,600 times to business audiences. Wrote the (dBase-II) code for his first database in 1985 and has been at the forefront of database use ever since.
He is an avid collector of books (printed in Antwerp) and vice-president of the Antwerp Bibliophile Society.
Area of Expertise
Solving (Historical) Research Issues With NeoDash
In this session, Guido will present how using NeoDash visualization in conjunction with a graph database can be a powerful tool for tackling intricate problems in historical and scientific research. Data in these fields are often scattered across the globe, residing in online databases with unique structures and semantics or only partially digitized within books. The task of linking these diverse sources with Linked Open Data presents its challenges.
Guido will introduce the "superconnector" – a knowledge graph designed to consolidate these disparate data sources, enhancing accessibility for researchers. The project to be discussed involves the compilation of data for 3,700 printers and publishers into well-structured profiles. By joining this session, you will gain a forward-looking perspective on leveraging graph databases and visualization tools to address research complexities.
Making graphs more user-friendly with AI
In his Nodes2023 session, Guido presented an elaborate NeoDash visualization of a knowledge graph intended to facilitate historical research.
Focusing on the printing industry in the Belgian city of Antwerp through the ages, the dataset now consists of 200K+ nodes and 260K+ relationships with data on 5,500+ persons. All of which were entered… manually. Not exactly database manager friendly!
End-users can easily find information on the NeoDash dashboard, but only represented in the way the designer wanted. Tailor-made queries are needed for all other research questions. Not the most enduser-friendly way…
ChatGPT to the rescue!
Inputwise, they have trained a ChatGPT persona to extract relevant data from OCR-readable PDF-files, compare them with the information in the graph and present the outcome for manual arbitrage. On average, this reduces data entry time by 80%.
Outputwise, they have created a ChatGPT-based UI that enables end-users to obtain natural language answers to any natural language question about the full content of the dataset. This was done by utilizing OpenAI’s API and Neo4j’s API to translate prompts to Cypher queries, run them and translate the results back to natural language.
When a user submits a question, a request is sent to OpenAI’s API using the o3-mini model. The model responds with a Cypher query that represents the user's intent.
After running the Cypher query through the Neo4J API, Neo4j responds with the raw query results in JSON — rows of data and column names.
The question, query and results are then fed back into the model which turns the data into a concise, natural-language answer.
This whole endeavor is a Wordpress plugin that allows for integration anywhere on the website, not bound by the constraints of an iframe.
By joining this session, you will learn how relatively basic AI-applications can turn a graph database into an even more powerful research tool in the hands of the end-users.
(description as per June 2025; improvements might still be made by October 2025!)
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top