Triple

T13623447
Position Surface form Disambiguated ID Type / Status
Subject Donnie Shell E325515 entity
Predicate notableTeammate P2649 FINISHED
Object Joe Greene E68430 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: Joe Greene | Statement: [Donnie Shell, notableTeammate, Joe Greene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Greene
Context triple: [Donnie Shell, notableTeammate, Joe Greene]
  • A. Joe Greene chosen
    Joe Greene is a legendary Pro Football Hall of Fame defensive tackle who anchored the Pittsburgh Steelers' dominant "Steel Curtain" defense in the 1970s.
  • B. Frank Clark
    Frank Clark was an early 20th-century American film actor known for his roles in silent-era adventure and drama productions.
  • C. Franco Harris
    Franco Harris was a Hall of Fame NFL running back best known for his role in the Pittsburgh Steelers’ 1970s dynasty and the iconic “Immaculate Reception.”
  • D. Gale Sayers
    Gale Sayers was a Hall of Fame NFL running back for the Chicago Bears, renowned for his electrifying speed and elusive running style during the 1960s.
  • E. Elmer Davis
    Elmer Davis was an American news reporter, author, and government official best known for leading U.S. propaganda and information efforts during World War II.
  • 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_69d8076aae28819092cf636190ee5529 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbbe9b0b648190afee93121483f45f completed April 12, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7942e8c9c8190ab843cc4c31f512a completed May 3, 2026, 6:30 p.m.
Created at: April 9, 2026, 9:50 p.m.