Triple

T7970765
Position Surface form Disambiguated ID Type / Status
Subject The Wasp E185316 entity
Predicate realName P9233 FINISHED
Object Janet van Dyne E328811 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: Janet van Dyne | Statement: [The Wasp, realName, Janet van Dyne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janet van Dyne
Context triple: [The Wasp, realName, Janet van Dyne]
  • A. Janet van Dyne chosen
    Janet van Dyne is a Marvel Comics superhero best known as the Wasp, a founding member of the Avengers and a longtime partner of Hank Pym.
  • B. Joelle Van Dyne
    Joelle Van Dyne is a central, enigmatic figure in David Foster Wallace’s novel "Infinite Jest," known for her extreme beauty, disfigured face, and involvement with both the film industry and the novel’s themes of addiction and obsession.
  • C. Hope van Dyne
    Hope van Dyne is a Marvel Comics and Marvel Cinematic Universe character who becomes the superhero Wasp, fighting alongside Ant-Man with a technologically advanced shrinking suit.
  • D. Elasti-Woman
    Elasti-Woman is a DC Comics superheroine and member of the Doom Patrol who can dramatically alter the size and shape of her body.
  • E. Martha Coleman
    Martha Coleman is a film producer known for her work on the British comedy-drama "Praise."
  • 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_69ca8297699481909b75a405f01e03af completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3bd304dc8190b9feee5e17fc66db completed March 31, 2026, 3:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc9387aabc81909ca13ee6a51525f4 completed April 1, 2026, 3:39 a.m.
Created at: March 30, 2026, 5:13 p.m.