Triple

T16026669
Position Surface form Disambiguated ID Type / Status
Subject Mundaneum E388733 entity
Predicate hasPart P35 FINISHED
Object Universal Bibliographic Repertory E1188613 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Universal Bibliographic Repertory | Statement: [Mundaneum, hasPart, Universal Bibliographic Repertory]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Universal Bibliographic Repertory
Context triple: [Mundaneum, hasPart, Universal Bibliographic Repertory]
  • A. universal bibliographic repertory chosen
    The universal bibliographic repertory was an ambitious late-19th- and early-20th-century project by Paul Otlet and Henri La Fontaine to create a comprehensive, card-based index of all the world’s published knowledge.
  • B. UNBIS Thesaurus
    The UNBIS Thesaurus is a controlled vocabulary used by the United Nations for indexing and retrieving documents and information across its bibliographic and information systems.
  • C. BNF bibliographic database
    The BNF bibliographic database is the comprehensive online catalog of the Bibliothèque nationale de France, providing detailed bibliographic records for its collections of books, manuscripts, and other documents.
  • D. BibDesk
    BibDesk is a macOS reference management application designed to help users organize and cite bibliographic data, especially for LaTeX documents.
  • E. Grunigen Medical Library
    Grunigen Medical Library is the primary health sciences and medical research library serving the University of California, Irvine’s medical center and related programs.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18328707c8190b9a444c78faaaa04 completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf31c8d8819096c562ba1453f3c0 completed May 10, 2026, 12:20 a.m.
Created at: April 10, 2026, 4:56 a.m.