Triple

T17065287
Position Surface form Disambiguated ID Type / Status
Subject Virgil Williams E414067 entity
Predicate collaboratedWith P435 FINISHED
Object Hillary Jordan 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: Hillary Jordan | Statement: [Virgil Williams, collaboratedWith, Hillary Jordan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hillary Jordan
Context triple: [Virgil Williams, collaboratedWith, Hillary Jordan]
  • A. Hillary Jordan chosen
    Hillary Jordan is an American novelist best known for her award-winning debut novel "Mudbound," a historical drama exploring race, family, and hardship in the Jim Crow-era Mississippi Delta.
  • B. Anna Jordan
    Anna Jordan is a musician and composer known for creating music for the film "Breakfast on Pluto."
  • C. Nessa Jenkins
    Nessa Jenkins is a deadpan, no-nonsense Welsh character from the British sitcom "Gavin & Stacey," known for her eccentric stories and iconic catchphrases.
  • D. Roslyn Jordan
    Roslyn Jordan is one of the daughters of Deloris Jordan and a member of the family of basketball legend Michael Jordan.
  • E. Rachel Scott
    Rachel Scott was a 17-year-old student, aspiring writer, and the first person killed in the Columbine High School shooting, later remembered for her journals and advocacy for kindness.
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3db806de48190a9ce68b40fc77a74 completed April 18, 2026, 7:29 p.m.
Created at: April 10, 2026, 5:34 a.m.