Triple

T10898414
Position Surface form Disambiguated ID Type / Status
Subject Ms. Marvel E257369 entity
Predicate featuresCharacter P626 FINISHED
Object Carol Danvers E508712 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: Carol Danvers | Statement: [Ms. Marvel, featuresCharacter, Carol Danvers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Danvers
Context triple: [Ms. Marvel, featuresCharacter, Carol Danvers]
  • A. Monica Rambeau
    Monica Rambeau is a Marvel Comics superhero and S.W.O.R.D. agent who gains energy-based powers and becomes a key figure in the Marvel Cinematic Universe.
  • B. Natasha Romanoff
    Natasha Romanoff, also known as Black Widow, is a highly skilled spy and assassin turned superhero in the Marvel Cinematic Universe and Marvel Comics.
  • C. Ms. Marvel (Carol Danvers) chosen
    Ms. Marvel (Carol Danvers) is a prominent Marvel Comics superheroine, later known as Captain Marvel, who gained superhuman strength, flight, and energy powers and became a key member of the Avengers.
  • D. Daisy Johnson
    Daisy Johnson is a powerful Inhuman superhero and skilled S.H.I.E.L.D. agent in Marvel Comics, best known by the codename Quake for her seismic vibration abilities and leadership roles.
  • E. Gwen Tyler
    Gwen Tyler is a fictional character featured in a toy line, likely designed as part of a themed set or narrative-driven collection.
  • 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_69d6aa8550c8819095508a2ed9acf3db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75d03a3fc81908df039b9b5ab9ca2 completed April 9, 2026, 8:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69e15524ec5c8190a330ce5fc16dd11d completed April 16, 2026, 9:31 p.m.
Created at: April 8, 2026, 9:21 p.m.