Stitching History into Semantics: LLM-Supported Knowledge Graph Engineering for 19th-Century Greek Bookbinding
Open Access
- 24 June 2025
- journal article
- research article
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (3) , 59
Abstract
Preserving cultural heritage can be efficiently supported by structured and semantic representation of historical artifacts. Bookbinding, a critical aspect of book history, provides valuable insights into past craftsmanship, material use, and conservation practices. However, existing bibliographic records often lack the depth needed to analyze bookbinding techniques, provenance, and preservation status. This paper presents a proof-of-concept system that explores how Large Language Models (LLMs) can support knowledge graph engineering within the context of 19th-century Greek bookbinding (1830–1900), and as a result, generate a domain-specific ontology and a knowledge graph. Our ontology encapsulates materials, binding techniques, artistic styles, and conservation history, integrating metadata standards like MARC and Dublin Core to ensure interoperability with existing library and archival systems. To validate its effectiveness, we construct a Neo4j knowledge graph, based on the generated ontology and utilize Cypher Queries—including LLM-generated queries—to extract insights about bookbinding practices and trends. This study also explores how semantic reasoning over the knowledge graph can identify historical binding patterns, assess book conservation needs, and infer relationships between bookbinding workshops. Unlike previous bibliographic ontologies, our approach provides a comprehensive, semantically rich representation of bookbinding history, methods and techniques, supporting scholars, conservators, and cultural heritage institutions. By demonstrating how LLMs can assist in ontology/KG creation and query generation, we introduce and evaluate a semi-automated pipeline as a methodological demonstration for studying historical bookbinding, contributing to digital humanities, book conservation, and cultural informatics. Finally, the proposed approach can be used in other domains, thus, being generally applicable in knowledge engineering.Keywords
This publication has 22 references indexed in Scilit:
- A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): models, evaluation metrics, benchmarks, and challengesDiscover Artificial Intelligence, 2024
- Ontology and collaborative data annotation for the standardisation of documentation processes of underground heritage spacesJournal of Cultural Heritage, 2024
- An Ontology-Based Framework for Supporting Decision-Making in Conservation and Restoration Interventions for Cultural HeritageJournal on Computing and Cultural Heritage, 2024
- CHEKG: a collaborative and hybrid methodology for engineering modular and fair domain-specific knowledge graphsKnowledge and Information Systems, 2024
- A Survey on Evaluation of Large Language ModelsACM Transactions on Intelligent Systems and Technology, 2024
- Cultural Heritage Information Retrieval: Past, Present, and Future TrendsIEEE Access, 2024
- Sharing the knowledge: exploring cultural heritage through an ontology-based platformJournal of Ambient Intelligence and Humanized Computing, 2023
- An Ontology for Modeling Cultural Heritage Knowledge in Urban TourismIEEE Access, 2022
- Filling the gap: new approaches to medieval bookbinding studiesJournal of Medieval Iberian Studies, 2022
- Using digital humanity approaches to visualize and evaluate the cultural heritage ontologyThe Electronic Library, 2021