Triple

T2596065
Position Surface form Disambiguated ID Type / Status
Subject Bill Bradley E58233 entity
Predicate familyName P18 FINISHED
Object Bradley E153144 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: Bradley | Statement: [Bill Bradley, familyName, Bradley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bradley
Context triple: [Bill Bradley, familyName, Bradley]
  • A. Bradley
    Bradley is the given first name of Brad Stevens, an American professional basketball executive and former head coach of the Boston Celtics.
  • B. Bradley chosen
    Bradley is a common English surname borne by numerous notable individuals across sports, politics, entertainment, and other fields.
  • C. Bradley
    Bradley is a locality in England historically associated with the life and death of the pioneering ironmaster John Wilkinson.
  • D. Ed Bradley
    Ed Bradley was an acclaimed American broadcast journalist best known as a pioneering and long-serving correspondent on the CBS news magazine program "60 Minutes."
  • E. Jack Bradley
    Jack Bradley is an American local politician who serves as the mayor of Lorain, Ohio.
  • 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_69ab4ac14040819098b13f4a27d5c8ff completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd42b3cd4819093b2cab78de1f66c completed March 7, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69af83c798088190944e7d754aa9aa06 completed March 10, 2026, 2:36 a.m.
Created at: March 6, 2026, 9:49 p.m.