Triple

T3921920
Position Surface form Disambiguated ID Type / Status
Subject DeVos family E88979 entity
Predicate foundedBy P104 FINISHED
Object Jay Van Andel E213027 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: Jay Van Andel | Statement: [DeVos family, foundedBy, Jay Van Andel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jay Van Andel
Context triple: [DeVos family, foundedBy, Jay Van Andel]
  • A. Jay Van Andel chosen
    Jay Van Andel was an American businessman and philanthropist best known as the co-founder of Amway and a major benefactor in Grand Rapids, Michigan.
  • B. Jan T. Kleyna
    Jan T. Kleyna is an astronomer known for discovering outer irregular moons of Jupiter, including Taygete.
  • C. James Heerdegen
    James Heerdegen is an American camera technician and dolly grip best known to the public for his former marriage to actress Christina Ricci.
  • D. Fred J. Koenekamp
    Fred J. Koenekamp was an American cinematographer renowned for his work on major films of the 1970s and 1980s, earning an Academy Award and multiple nominations for his visually striking photography.
  • E. Leo Beenhakker
    Leo Beenhakker is a Dutch football manager renowned for coaching top clubs and national teams, including Real Madrid, Ajax, and 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_69aed955229881909e85e73ffab1d343 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed7a553c81909b65f8287293ecac completed March 9, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5286c807481908a67471da777b264 completed March 14, 2026, 9:20 a.m.
Created at: March 9, 2026, 3:22 p.m.