Triple

T11770109
Position Surface form Disambiguated ID Type / Status
Subject Sharon Carter E279873 entity
Predicate associatedWith P37 FINISHED
Object Black Widow E912715 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: Black Widow | Statement: [Sharon Carter, associatedWith, Black Widow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Black Widow
Context triple: [Sharon Carter, associatedWith, Black Widow]
  • A. Black Widow
    "Black Widow" is a 2021 Marvel Cinematic Universe superhero film centered on Natasha Romanoff that explores her past as a spy and her ties to a covert Russian program.
  • B. Black Widow
    Black Widow is a modernist sculptural mobile by Alexander Calder, exemplifying his innovative use of abstract forms and suspended movement.
  • C. Black Widow
    Black Widow is a giant pendulum thrill ride at Kennywood amusement park known for its high-speed swinging and spinning motions that create intense sensations of weightlessness.
  • D. Black Widow
    "Black Widow" is a 2014 hip hop/pop single by Australian rapper Iggy Azalea featuring Rita Ora, known for its catchy hook and revenge-themed lyrics.
  • E. Black Widow chosen
    Black Widow is a highly skilled Marvel Comics spy and assassin, best known as Natasha Romanoff, a core member of the Avengers.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a55c9f988190b203b66a28c767ae completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f09086c4ec81908bc8b707a49c3ac2 completed April 28, 2026, 10:48 a.m.
Created at: April 8, 2026, 9:41 p.m.