Triple

T15566961
Position Surface form Disambiguated ID Type / Status
Subject The Soul Keeper E371140 entity
Predicate distributor P1951 FINISHED
Object Medusa Film E322787 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: Medusa Film | Statement: [The Soul Keeper, distributor, Medusa Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Medusa Film
Context triple: [The Soul Keeper, distributor, Medusa Film]
  • A. Medusa Film chosen
    Medusa Film is an Italian film production and distribution company known for backing a wide range of domestic and international movies.
  • B. Galatea Film
    Galatea Film is an Italian film production company known for backing genre and horror movies, including works by director Mario Bava.
  • C. Mantaray Film
    Mantaray Film is a Swedish film production company known for producing acclaimed documentaries and feature films, often with a strong focus on personal and artistic stories.
  • D. Athos Films
    Athos Films is a French film distribution company known for handling the release of notable art-house and New Wave films.
  • E. Diaphana Films
    Diaphana Films is a French film distribution and production company known for handling acclaimed international and auteur cinema.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04dde90b081908284d9258d4462e3 completed April 16, 2026, 2:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4219a081909acca9f783ecd44b completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:10 a.m.