Triple

T18821858
Position Surface form Disambiguated ID Type / Status
Subject Thor: Ragnarok (2017) film score E460280 entity
Predicate inUniverseCharacter P133542 FINISHED
Object Hela 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: Hela | Statement: [Thor: Ragnarok (2017) film score, inUniverseCharacter, Hela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hela
Context triple: [Thor: Ragnarok (2017) film score, inUniverseCharacter, Hela]
  • A. Hela chosen
    Hela is the Asgardian goddess of death and the primary antagonist in the Marvel Cinematic Universe film "Thor: Ragnarok."
  • B. Gorr the God Butcher
    Gorr the God Butcher is a vengeful Marvel Comics supervillain known for hunting and slaughtering gods across the universe after losing faith in them.
  • C. Mahates
    Mahates is a municipality and town in northern Colombia known for its Afro-Colombian cultural heritage and historical significance in the Bolívar Department.
  • D. Korvac
    Korvac is a powerful cosmic villain in Marvel Comics best known for battling the Avengers and the Guardians of the Galaxy in the classic "Korvac Saga."
  • E. Stryfe
    Stryfe is a powerful and ruthless Marvel Comics supervillain, a clone of Cable and frequent adversary of the X-Men and X-Force.
  • 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.