Triple

T18835643
Position Surface form Disambiguated ID Type / Status
Subject the Troll E460656 entity
Predicate createdByCharacter P40162 FINISHED
Object Charlie Kelly 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: Charlie Kelly | Statement: [the Troll, createdByCharacter, Charlie Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charlie Kelly
Context triple: [the Troll, createdByCharacter, Charlie Kelly]
  • A. Charlie Kelly chosen
    Charlie Kelly is a dim-witted yet oddly resourceful janitor and co-owner of Paddy’s Pub on the sitcom "It’s Always Sunny in Philadelphia," known for his chaotic behavior and bizarre schemes.
  • B. Charles Kelly
    Charles Kelly was the husband of renowned Victorian-era English actress Ellen Terry.
  • C. Bill Travers
    Bill Travers was a British actor and wildlife conservationist best known for his roles in mid-20th-century films and for co-founding the Born Free Foundation.
  • D. Eddie McClintock
    Eddie McClintock is an American actor best known for starring as Secret Service agent Pete Lattimer on the science fiction television series "Warehouse 13."
  • E. Rand McPherson
    Rand McPherson is the protagonist of the comedy film "PCU," a college student navigating the chaos and absurdities of campus life.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a99d491c81909d8e55ac45621d44 completed April 20, 2026, 4:20 a.m.
Created at: April 10, 2026, 11:56 a.m.