Triple

T22459477
Position Surface form Disambiguated ID Type / Status
Subject J.J. Voskuil E555192 entity
Predicate employer P7 FINISHED
Object Meertens Instituut NE NERFINISHED

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: Meertens Instituut | Statement: [J.J. Voskuil, employer, Meertens Instituut]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Meertens Instituut
Context triple: [J.J. Voskuil, employer, Meertens Instituut]
  • A. Meertens Institute chosen
    The Meertens Institute is a Dutch research center specializing in the study and documentation of language and culture in the Netherlands.
  • B. Meertens
    Meertens is a Dutch surname most notably associated with computer scientist Lambert Meertens, a key contributor to programming language design.
  • C. Afrikaanse Taalmuseum
    The Afrikaanse Taalmuseum is a cultural and linguistic museum in Paarl, South Africa, dedicated to the history, development, and preservation of the Afrikaans language.
  • D. Sandberg Instituut
    Sandberg Instituut is a renowned postgraduate art and design school in Amsterdam known for its experimental and research-driven programs.
  • E. Leiden University Libraries
    Leiden University Libraries is the academic library system of Leiden University in the Netherlands, renowned for its extensive historical and research collections.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e51fdec8190adfdf9f8a6362221 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b7e01fc8190825c3dc024484440 completed April 29, 2026, 1:14 a.m.
Created at: April 16, 2026, 8:48 p.m.