Triple

T16494000
Position Surface form Disambiguated ID Type / Status
Subject Doug and Maria DeVos Foundation E400635 entity
Predicate namedAfter P63 FINISHED
Object Maria DeVos E403163 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: Maria DeVos | Statement: [Doug and Maria DeVos Foundation, namedAfter, Maria DeVos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria DeVos
Context triple: [Doug and Maria DeVos Foundation, namedAfter, Maria DeVos]
  • A. Helen DeVos chosen
    Helen DeVos was an American philanthropist and arts patron, known for her extensive charitable work in healthcare, education, and the cultural life of Grand Rapids, Michigan.
  • B. Margaret DeVogelaere
    Margaret DeVogelaere is best known as the third wife of American actor Peter Fonda, with whom she was married from 2011 until his death in 2019.
  • C. Wilma Slaghoople
    Wilma Slaghoople is the younger version of Wilma Flintstone, depicted as a child in the animated series "The Flintstone Kids."
  • D. Antoinette Beumer
    Antoinette Beumer is a Dutch film director and screenwriter known for directing popular Dutch-language films and television productions.
  • E. Hilda Koopman
    Hilda Koopman is a prominent linguist known for her influential work in syntactic theory and generative grammar.
  • 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_69d883813098819084f5409539723b59 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e3189c8819097e6ba62f24b1f6c completed April 18, 2026, 7:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00607cbc80819088505d8bdd663109 completed May 10, 2026, 10:39 a.m.
Created at: April 10, 2026, 5:13 a.m.