Triple

T17818713
Position Surface form Disambiguated ID Type / Status
Subject Gillian Greene E444914 entity
Predicate notableRelative P367 FINISHED
Object Sam Raimi 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: Sam Raimi | Statement: [Gillian Greene, notableRelative, Sam Raimi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sam Raimi
Context triple: [Gillian Greene, notableRelative, Sam Raimi]
  • A. Sam Raimi chosen
    Sam Raimi is an American filmmaker best known for directing the original Spider-Man trilogy and creating the cult-favorite Evil Dead horror series.
  • B. Lorne Raimi
    Lorne Raimi is one of the children of American filmmaker Sam Raimi.
  • C. Ivan Raimi
    Ivan Raimi is an American physician and screenwriter best known for co-writing several films and projects with his brother, director Sam Raimi.
  • D. Ted Raimi
    Ted Raimi is an American character actor and director known for his roles in cult horror and fantasy projects such as the Evil Dead series and the TV show Xena: Warrior Princess.
  • E. Raimi
    Raimi is a surname most notably associated with American filmmaker Sam Raimi and his family, known for their contributions to horror and superhero cinema.
  • 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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e488812df081909771d51c54c405fe completed April 19, 2026, 7:47 a.m.
Created at: April 10, 2026, 10:14 a.m.