Triple

T18821886
Position Surface form Disambiguated ID Type / Status
Subject Captain Marvel (2019) film score E460281 entity
Predicate associatedCharacter P12208 FINISHED
Object Yon-Rogg 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: Yon-Rogg | Statement: [Captain Marvel (2019) film score, associatedCharacter, Yon-Rogg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yon-Rogg
Context triple: [Captain Marvel (2019) film score, associatedCharacter, Yon-Rogg]
  • A. Yon-Rogg chosen
    Yon-Rogg is a Kree military commander and mentor-turned-antagonist to Carol Danvers in the Marvel Cinematic Universe film "Captain Marvel."
  • B. Bossk
    Bossk is a reptilian Trandoshan bounty hunter in the Star Wars universe, known for his ruthless nature and frequent work alongside other infamous hunters.
  • C. Greef Karga
    Greef Karga is a character in the Star Wars universe, featured in the series "The Mandalorian" as a leader within the Bounty Hunters' Guild who becomes an ally to the titular Mandalorian.
  • D. Lor-Van
    Lor-Van is a Kryptonian scientist from DC Comics lore, best known as the father of Superman’s mother, Lara.
  • E. Phasma
    Phasma is a Star Wars novel by Delilah S. Dawson that explores the ruthless origins and rise of Captain Phasma of the First Order.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6ba90988190a93e1c2fa23b3d1d completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:55 a.m.