Triple

T1101001
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl I E24378 entity
Predicate mvp P2630 FINISHED
Object Bart Starr E53002 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: Bart Starr | Statement: [Super Bowl I, mvp, Bart Starr]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bart Starr
Context triple: [Super Bowl I, mvp, Bart Starr]
  • A. Bart Starr chosen
    Bart Starr was a Hall of Fame NFL quarterback and legendary leader of the Green Bay Packers who guided the team to multiple championships in the 1960s.
  • B. Bob Griese
    Bob Griese is a Hall of Fame former NFL quarterback for the Miami Dolphins who later became a prominent football television analyst.
  • C. Hank Stram
    Hank Stram was an American football coach best known for leading the Kansas City Chiefs to early AFL success and victory in Super Bowl IV.
  • D. Len Dawson
    Len Dawson was an American Hall of Fame quarterback best known for leading the Kansas City Chiefs to victory in Super Bowl IV and later working as a prominent football broadcaster.
  • E. Jack Ham
    Jack Ham is a Pro Football Hall of Fame linebacker renowned for his key role in the Pittsburgh Steelers' dominant defenses of the 1970s.
  • 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_69a4940542308190ac2a0b1f730b7cfc completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9c079f48190a0e0ddda182f7a01 completed March 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac763a7cd481909bf83a2e67c0d9f5 completed March 7, 2026, 7:02 p.m.
Created at: March 1, 2026, 7:43 p.m.