PKG API: A Tool for Personal Knowledge Graph Management

TL;DR

The paper tackles the lack of practical, user-friendly personal knowledge graph tools by introducing an end-to-end PKG solution consisting of a web client and a service API. It builds an RDF-based PKG vocabulary with provenance and access-control for structured statement representation and enables natural-language interaction via NL2PKG, translating NL statements into SPARQL actions. Key contributions include the RDF reification-based PKG vocabulary, the NL2PKG two-stage pipeline (intent extraction and entity linking), and a modular implementation (Flask API, React client, LLM-backed NL processing) along with an open-source demo. This approach aims to make PKGs accessible to non-expert users while preserving data ownership and enabling fine-grained access control and provenance tracking.

Abstract

Personal knowledge graphs (PKGs) offer individuals a way to store and consolidate their fragmented personal data in a central place, improving service personalization while maintaining full user control. Despite their potential, practical PKG implementations with user-friendly interfaces remain scarce. This work addresses this gap by proposing a complete solution to represent, manage, and interface with PKGs. Our approach includes (1) a user-facing PKG Client, enabling end-users to administer their personal data easily via natural language statements, and (2) a service-oriented PKG API. To tackle the complexity of representing these statements within a PKG, we present an RDF-based PKG vocabulary that supports this, along with properties for access rights and provenance.

Figures (3)

• Figure 1: Overview of the PKG tooling developed in this work.
• Figure 2: Screenshot of the home screen after submission of a natural language statement.
• Figure 3: Life of a statement from NL to PKG.