Triple

T22391160
Position Surface form Disambiguated ID Type / Status
Subject Fire Away E553513 entity
Predicate writer P1360 FINISHED
Object Danny Green 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: Danny Green | Statement: [Fire Away, writer, Danny Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Danny Green
Context triple: [Fire Away, writer, Danny Green]
  • A. Danny Green
    Danny Green is an American professional basketball shooting guard known for his three-point shooting and perimeter defense, who has won multiple NBA championships with different teams.
  • B. Danny Green chosen
    Danny Green is a film editor known for his work on the classic British comedy "The Man in the White Suit."
  • C. Jeff Green
    Jeff Green is an American professional basketball player and NBA veteran known for his versatility as a forward and long career with numerous teams across the league.
  • D. Adriel Jeremiah Green
    Adriel Jeremiah Green is a former American football wide receiver best known for his Pro Bowl career with the Cincinnati Bengals in the NFL.
  • E. Gerald Green
    Gerald Green is an American former professional basketball player best known for his high-flying athleticism and memorable slam dunks during his NBA career.
  • 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_69e11e4cf87c8190a1ff474daec326b7 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1585b56208190b53b90a81a807a9d completed April 29, 2026, 1:01 a.m.
Created at: April 16, 2026, 8:45 p.m.