Triple

T34976008
Position Surface form Disambiguated ID Type / Status
Subject Krakozhia E1008677 entity
Predicate governingAuthorityInFilm P203493 FINISHED
Object Krakozhian government 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: Krakozhian government | Statement: [Krakozhia, governingAuthorityInFilm, Krakozhian government]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: governingAuthorityInFilm
Context triple: [Krakozhia, governingAuthorityInFilm, Krakozhian government]
  • A. ownedByInFilm
    Indicates that one entity is portrayed as being owned or possessed by another entity within the context of a specific film.
  • B. hasFilmCertificationAuthority
    Indicates that an entity (such as a film or film-related jurisdiction) is associated with the authority or organization responsible for certifying or rating that film.
  • C. managerInFilm
    Indicates that one entity serves as the manager of another entity within the context of a specific film.
  • D. inheritedByInFilm
    Indicates that a character, role, or attribute is passed on or taken over by another character within the narrative of a film.
  • E. directorInUniverse
    Indicates that one entity serves as the director of another entity within a specific fictional or defined universe or continuity.
  • F. None of above. chosen

Provenance (4 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_69f76dc78a308190a1ac29ad4a9a4895 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_6a019037edbc8190bdaec436ac2fcec6 completed May 11, 2026, 8:15 a.m.
PD Predicate disambiguation batch_6a018fe05a34819080068f588b5ff80c completed May 11, 2026, 8:14 a.m.
PDg Predicate description generation batch_6a0190370290819096183e9fb7d32cff completed May 11, 2026, 8:15 a.m.
Created at: May 3, 2026, 4:01 p.m.