Triple

T7815951
Position Surface form Disambiguated ID Type / Status
Subject Grady Wilson E181007 entity
Predicate friendOf P8712 FINISHED
Object Bubba Bexley E173470 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: Bubba Bexley | Statement: [Grady Wilson, friendOf, Bubba Bexley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bubba Bexley
Context triple: [Grady Wilson, friendOf, Bubba Bexley]
  • A. Bubba Bexley chosen
    Bubba Bexley is a recurring comedic character and friend of Fred Sanford on the classic American sitcom "Sanford and Son."
  • B. Bubba Higgins
    Bubba Higgins is a dim-witted but good-hearted teenage grandson in the sitcom "Mama’s Family," known for his comedic mishaps and close relationship with his sharp-tongued grandmother, Thelma Harper.
  • C. Bubba Paris
    Bubba Paris is a former American football offensive tackle best known for his NFL career with the San Francisco 49ers, with whom he won multiple Super Bowls in the 1980s.
  • D. Benjamin Buford "Bubba" Blue
    Benjamin Buford "Bubba" Blue is a shrimp-obsessed, soft-spoken Vietnam War soldier and close friend of Forrest Gump in the film "Forrest Gump."
  • E. Booger McFarland
    Booger McFarland is a former NFL defensive tackle who became a prominent American football television analyst and color commentator.
  • 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_69ca828153f48190bdb27ac46f8e0745 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69caf96d1f088190a1d005ffb019afe9 completed March 30, 2026, 10:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb1488a2e48190924f44b46f925d87 completed March 31, 2026, 12:25 a.m.
Created at: March 30, 2026, 4:39 p.m.