Building Trustworthy Knowledge Systems Through Ontology and Deterministic Reasoning
Why This Session
This session unpacks the principles behind a hybrid knowledge system that combines LLM extraction with deterministic Datalog verification. The goal is to give you the practical design skills to structure your organization's knowledge assets into a source-backed, ontology-based knowledge base (KB).
Rather than trying to prompt LLM hallucination away, this session tackles it at the level of the knowledge system itself. We'll walk through, from first principles, a hybrid architecture that combines LLMs, ontologies, and Datalog — where the LLM extracts knowledge from documents, a human reviews and approves it, and a deterministic Datalog reasoning engine verifies it for contradictions and policy violations — and see the entire pipeline in action through a demo of the open-source tool factlog. You'll come away understanding how to build a verifiable, source-backed knowledge base, and the design patterns for extending it into an organization-wide ontology-based knowledge system.
About the Speaker
Jeongseok Kim holds a PhD in Artificial Intelligence and brings over 20 years of experience in systems architecture design and project management. As CEO of Cleverplant, a company building neuro-symbolic AI decision-support systems, he leads the creation of business value through the convergence of ontologies and intelligent solutions. He has applied AI in real-world settings — ontology-based data analysis, standardization strategy, and open-source stack design — at global IT consulting firms and major corporations including SK Telecom and LG Electronics, and teaches practical ontology courses as an educator in the field of Knowledge Engineering.
See the Design Principles Behind Trustworthy Knowledge Systems
This is a free 60-minute session. See a live demo of factlog and learn how to design and extend a verifiable knowledge system.
Register for the Conference