Triple

T6186237
Position Surface form Disambiguated ID Type / Status
Subject Johannes Kleiman E138066 entity
Predicate workedWith P398 FINISHED
Object Bep Voskuijl E64316 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: Bep Voskuijl | Statement: [Johannes Kleiman, workedWith, Bep Voskuijl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bep Voskuijl
Context triple: [Johannes Kleiman, workedWith, Bep Voskuijl]
  • A. Bep Voskuijl chosen
    Bep Voskuijl was a Dutch office worker who helped hide Anne Frank and her family during World War II by providing food, supplies, and support to those in the Secret Annex.
  • B. Piet de Jong
    Piet de Jong was a Dutch politician who served as Prime Minister of the Netherlands from 1967 to 1971.
  • C. Piet Keizer
    Piet Keizer was a renowned Dutch footballer, best known as a skillful left winger for Ajax and the Netherlands national team during the late 1960s and early 1970s.
  • D. Piet Klijnveld
    Piet Klijnveld was a Dutch accountant and entrepreneur who co-founded the international professional services firm that later became part of KPMG.
  • E. Koos Vorrink
    Koos Vorrink was a prominent Dutch social-democratic politician and trade union leader who played a key role in shaping the modern Labour Party (PvdA) in the Netherlands.
  • 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0621671988190938dd16242a2e4d5 completed March 22, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c65fadf36c819091b57c2c390f72b5 completed March 27, 2026, 10:45 a.m.
Created at: March 22, 2026, 4:19 p.m.