Triple

T10467238
Position Surface form Disambiguated ID Type / Status
Subject Kate & Leopold E246828 entity
Predicate screenwriter P2831 FINISHED
Object Steven Rogers E633753 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: Steven Rogers | Statement: [Kate & Leopold, screenwriter, Steven Rogers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven Rogers
Context triple: [Kate & Leopold, screenwriter, Steven Rogers]
  • A. Steven Rogers chosen
    Steven Rogers is an American screenwriter known for writing character-driven dramas and comedies, including the film "Hope Floats."
  • B. Steve Rogers
    Steve Rogers is the Marvel Comics superhero better known as Captain America, a World War II-era super-soldier and iconic leader of the Avengers.
  • C. Nick Fury
    Nick Fury is the one-eyed, trench-coat-wearing spymaster and director of S.H.I.E.L.D. who orchestrates and oversees the Avengers in the Marvel universe.
  • D. Sam Wilson
    Sam Wilson is a Marvel Comics superhero better known as the Falcon, an ally of Captain America who later takes up the Captain America mantle himself.
  • E. Bucky Barnes
    Bucky Barnes is a Marvel Comics character best known as Captain America's childhood friend who becomes the brainwashed assassin Winter Soldier before seeking redemption.
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5092e3230819098ab444f73c9bd40 completed April 7, 2026, 1:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89ff1cd948190a1ef331fb810bf26 completed April 10, 2026, 7 a.m.
Created at: April 6, 2026, 12:20 p.m.