Triple

T23011413
Position Surface form Disambiguated ID Type / Status
Subject Robyn Hayward E572913 entity
Predicate notableRelative P367 FINISHED
Object Gordon Hayward 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: Gordon Hayward | Statement: [Robyn Hayward, notableRelative, Gordon Hayward]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gordon Hayward
Context triple: [Robyn Hayward, notableRelative, Gordon Hayward]
  • A. Gordon Hayward chosen
    Gordon Hayward is an American professional basketball player, best known for his NBA career and for leading Butler University to back-to-back NCAA championship game appearances.
  • B. Michael Peirce
    Michael Peirce is a political figure who ran for governor in New Hampshire’s 2018 gubernatorial election.
  • C. Jordan Clarkson
    Jordan Clarkson is a Filipino-American professional basketball guard known for his prolific scoring off the bench in the NBA.
  • D. Avery Bradley
    Avery Bradley is an American professional basketball guard known for his elite perimeter defense and key role on contending NBA teams, including the Los Angeles Lakers.
  • E. Josh Hart
    Josh Hart is an American professional basketball player and former Villanova University standout known for his versatility, rebounding, and two-way play on the wing.
  • 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1835b0cb881908d3d2dd40cffcbc2 completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:51 p.m.