CHAD-KG: A Knowledge Graph for Representing Cultural Heritage Objects and Digitisation Paradata

2025-05-19

AI Summary

To address semantic fragmentation and weak interoperability between bibliographic metadata and digital processual data (paradata) in cultural heritage datasets, this paper introduces CHAD-KG, a knowledge graph for cultural heritage digitization. Methodologically, it pioneers the integration of international standards—particularly CIDOC-CRM—with an original OWL application profile, CHAD-AP, to systematically model the full semantics of the digitization workflow; it further proposes a reproducible Morph-KGC-based RDF conversion pipeline to ensure high-quality knowledge graph generation. Key contributions include: (1) the open-source CHAD-KG (released under CC0), accessible via a SPARQL endpoint, interactive web interface, and Zenodo-hosted dataset; (2) practical deployment in the “Another Renaissance” temporary exhibition’s digital twin; and (3) integration into the national CHANGES project. CHAD-KG provides a scalable methodology and foundational infrastructure for museum digital twins and semantic interoperability across heterogeneous cultural heritage systems.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Description Logics
• Application Domains: Humanities & Computational Social Science

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

This paper presents CHAD-KG, a knowledge graph designed to describe bibliographic metadata and digitisation paradata of cultural heritage objects in exhibitions, museums, and collections. It also documents the related data model and materialisation engine. Originally based on two tabular datasets, the data was converted into RDF according to CHAD-AP, an OWL application profile built on standards like CIDOC-CRM, LRMoo, CRMdig, and Getty AAT. A reproducible pipeline, developed with a Morph-KGC extension, was used to generate the graph. CHAD-KG now serves as the main metadata source for the Digital Twin of the temporary exhibition titled emph{The Other Renaissance - Ulisse Aldrovandi and The Wonders Of The World}, and other collections related to the digitisation work under development in a nationwide funded project, i.e. Project CHANGES (https://fondazionechanges.org). To ensure accessibility and reuse, it offers a SPARQL endpoint, a user interface, open documentation, and is published on Zenodo under a CC0 license. The project improves the semantic interoperability of cultural heritage data, with future work aiming to extend the data model and materialisation pipeline to better capture the complexities of acquisition and digitisation, further enrich the dataset and broaden its relevance to similar initiatives.

Problem

• Represent cultural heritage objects and digitisation paradata semantically
• Convert tabular data to RDF using standards-based application profile
• Enhance interoperability and reuse of cultural heritage metadata

Innovation

• Knowledge graph for cultural heritage metadata
• RDF conversion using CHAD-AP standards
• Morph-KGC extension for reproducible pipeline