Automated Construction of FAIR Digital Object Knowledge Graphs from Flat Cultural Heritage Records
2026-08-24 • Artificial Intelligence
Artificial IntelligenceComputation and LanguageDigital Libraries
AI summaryⓘ
The authors worked on making Europeana's cultural heritage data easier for computers to understand and use by turning plain text descriptions into structured digital objects with unique identifiers. They used a special model called CIDOC-CRM and a large language model to decide which data should link to other known entities and which should stay as simple text. Testing on archaeological records showed this method connected most data points and improved links that Europeana hadn’t made before. Their approach ensures every piece of data is clearly defined and can be followed by software across records.
FAIR Digital Object (FDO)Persistent Identifier (PID)Europeana Data ModelCIDOC-CRMLarge Language Model (LLM)Knowledge GraphControlled VocabularyGetty AATWikidataEntity Linking
Authors
Zeyd Boukhers, Lingxiao Kong, Xenophon Zabulis, Georgios Toubekis
Abstract
The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to produce a fully machine-actionable graph in which every reference is resolvable. The Europeana Data Model was designed long before the FDO specification, and it stores most metadata values as plain text. This serves human browsing well enough, but gives an automated agent nothing to follow across records or collections. We present a pipeline that transforms flat Europeana records into an FDO-compliant knowledge graph structured with CIDOC-CRM. Following the FDO specification, we model every heritage entity as a discrete FDO with its own PID, type, profile, and metadata layer. The core technical challenge is automating the FDO-prescribed distinction between values that must become PID references (resolvable entities) and those that may remain literals (terminal leaves such as notes, measurements, and dates). We address this with a large language model that classifies each metadata value, routes it to a controlled vocabulary (Getty AAT, Wikidata, VIAF, PeriodO), and links it to a shared entity FDO. We evaluate using 637 archaeological records from five Europeana providers, processing each with the LLM. The pipeline links 86% of metadata slots, resolving 58.5% of values Europeana had not already enriched. It also merges cross-lingual surface forms that byte-identical matching keeps apart, where 17 of 33 such merges are correct on manual review. Graph connectivity does not separate this from string matching; what distinguishes the FDO graph is that every node is typed and resolvable.