preprintZenodo (CERN European Organization for Nuclear Research)Mar 14, 2026GREEN OA

Fact Extraction via Canonical Identifiers: Validating a Multi-Registry Pipeline for Dutch Open Data

RMRogier Meulenaar

Radboud University Nijmegen

Indexed indatacite

Abstract

Paper 4 in the Prioris research series. Validates fact-level edge extraction using seven Dutch canonical identifier types (BIG, ECLI, KvK, SKJ, QID, BRIN, AGB). Reports precision and recall per identifier type, compares regex vs spaCy NER, and demonstrates cross-registry verification for accountability use cases. Part of the research programme (Paper 0: 10.5281/zenodo.19024611).

Citation impact

12
total citations
FWCI
—
Percentile
—
References
0
Too recent for citation history.

Authors

1

Topics & keywords

Topics
Keywords
  • Identifier
  • Pipeline (software)
  • Precision and recall
  • Real world data
  • Base (topology)
  • Encoding (memory)
  • Extraction (chemistry)
  • Data modeling
No related works found for this paper.