Triple

T18945388
Position Surface form Disambiguated ID Type / Status
Subject Jack Porter E463498 entity
Predicate hasName P744 FINISHED
Object Jack Porter 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: Jack Porter | Statement: [Jack Porter, hasName, Jack Porter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Porter
Context triple: [Jack Porter, hasName, Jack Porter]
  • A. Jack Porter chosen
    Jack Porter is a central character in the TV drama "Revenge," known as a loyal, morally grounded bar owner whose life becomes deeply entangled in Emily Thorne’s quest for vengeance.
  • B. Jack Porter
    Jack Porter is a central character in the TV drama "Watch Over Me," portrayed as a protective and emotionally complex figure entangled in the show's romantic and suspenseful storylines.
  • C. Bob Porter
    Bob Porter is a central fictional character named in the work "Teachers," likely depicted as a key figure within an educational setting.
  • D. Ben Porterfield
    Ben Porterfield is a technology entrepreneur best known as a co-founder of the business intelligence and data analytics company Looker.
  • E. Jesse Porter
    Jesse Porter is a skilled and resourceful counterintelligence operative who becomes an ally to Michael Westen in the television series "Burn Notice."
  • 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_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d53f6eb8819099b1268db8b14d66 completed April 20, 2026, 7:26 a.m.
Created at: April 10, 2026, 11:59 a.m.