Triple

T15681665
Position Surface form Disambiguated ID Type / Status
Subject Bob Harris E377591 entity
Predicate name P16 FINISHED
Object Bob Harris E377591 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: Bob Harris | Statement: [Bob Harris, name, Bob Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bob Harris
Context triple: [Bob Harris, name, Bob Harris]
  • A. Bob Harris chosen
    Bob Harris is a middle-aged, fading American movie star who forms an unexpected emotional connection with a young woman while adrift in Tokyo in the film "Lost in Translation."
  • B. Bill Harris
    Bill Harris is an American politician who served as mayor of Lincoln, Nebraska, following Mike Johanns.
  • C. Phil Harris
    Phil Harris was an American bandleader, singer, comedian, and radio personality best known for his wisecracking persona on classic radio shows and his later voice work in Disney animated films.
  • D. Vic Harris
    Vic Harris was a prominent Negro league baseball figure best known for managing the powerhouse Homestead Grays during their era of dominance.
  • E. Keith Harris
    Keith Harris is a writer known for his contributions to the music and entertainment publication OMG.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f306a1c8190a819541a3cc51f5a completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ee2a33c81908fcd120ca670b309 completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:16 a.m.