From Relational and Property Graph Data to Large Language Models

2026-08-11

AI Summary

This work addresses the need for unified and efficient knowledge provisioning in large language models by proposing a novel architecture that integrates relational and property graph data models. The approach leverages record addresses from log files as immutable reference values in place of traditional foreign keys, enabling efficient graph-style link traversal instead of costly join queries while natively supporting triple-based knowledge representation. The resulting unified knowledge service framework combines the structural rigor of relational models with the flexible associative capabilities of graph models, significantly enhancing knowledge retrieval efficiency and effectively supporting knowledge integration and invocation in generative AI systems.

Abstract

A data management server that combines the relational data model found in traditional databases with the graphical models being developed by newer data products can provide its knowledge model to generative tools for large language models. Both models have been reconciled at the implementation level by replacing foreign keys by reference values. This boosts performance and allows effectively following links instead of lookup joins. The reference value will never change as it uses the record address in the log file. This paper reports on progress in providing such a synthesis and includes an example of a knowledge base that is triple-based and would also be supported in such a system.

Problem

• relational data
• property graph
• large language models
• knowledge representation
• data integration

Innovation

• reference values
• relational-graph integration
• log-based addressing
• foreign key replacement
• LLM knowledge model