Building a Hybrid Knowledge Graph System
KGC 2025
•
1h 30m
Giuseppe Futia, CSI - Piedmontese Consortium for Information Systems (Italy), Data Engineer
Knowledge Graphs (KGs) are essential for data integration and analytics, yet selecting the right technology stack remains challenging. While Label Property Graphs (LPG) enable the usage of powerful graph-based algorithms, Resource Description Framework (RDF) provides robust data interoperability, constraints, and reasoning. This hands-on tutorial guides participants in building a hybrid KG system that combines LPG and RDF, leveraging their strengths.
Using real-world open data from the City of Chicago—including business activities, licenses, organizations, and contracts—participants will address key governance and financial transparency challenges:
Entity Resolution & Financial Tracking: Connecting datasets to trace financial transactions and identify money flows for a unique entity.
Conflict of Interest Detection: Uncovering hidden relationships between businesses and financial transactions to flag ethical and regulatory concerns.
Regulatory Compliance & Risk Assessment: Detecting inconsistencies between contracts and assigned licenses by validating activities against constraint-based rules.
Additionally, the tutorial will show how LLMs enhance the interaction with the KG system, enabling intuitive exploration. By the end, attendees will gain hands-on experience integrating LPG and RDF while leveraging LLMs for insightful KG analysis.
This session is ideal for practitioners and researchers applying a hybrid, AI-powered KG approach to real-world problems.
Up Next in KGC 2025
-
The State of the Art LLMs for Knowled...
Nandana Mihindukulasooriya, IBM Research, Senior Research Scientist
Jennifer D`Souza, TIB Leibniz Information Centre for Science and Technology, Hannover, Germany, Postdoctoral ResearcherKnowledge graphs (KGs) play a crucial role in modern applications. However, automatically constructing a KG ...
-
Creating High-Quality Knowledge Graph...
Prashanth Rao, Kùzu, Inc, AI Engineer
Paco Nathan, Senzing, Principal DevRel EngineerAn important obstacle for adopting knowledge graph technology in enterprises is that virtually all of the enterprise-level data is originally stored in unstructured formats or in some structured but non-graph f...
-
The Ultimate Guide to Knowledge-Based AI
Valerio Cocchi, Oxford Semantic Technologies, Lead Knowledge Engineer
Knowledge-based AI has been launched into the mainstream as it serves as the antidote to LLM hallucinations in RAG systems—an increasingly visible feature but just one of many critical applications in which Knowledge-based AI ...