Triple

T21994599
Position Surface form Disambiguated ID Type / Status
Subject Insidious E543172 entity
Predicate director P255 FINISHED
Object James Wan 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: James Wan | Statement: [Insidious, director, James Wan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Wan
Context triple: [Insidious, director, James Wan]
  • A. James Wan chosen
    James Wan is a Malaysian-Australian filmmaker best known for creating the Saw and The Conjuring horror franchises and directing major blockbuster films in the DC Extended Universe.
  • B. Leigh Whannell
    Leigh Whannell is an Australian screenwriter, director, actor, and producer best known for co-creating the Saw and Insidious horror film franchises.
  • C. Mike Flanagan
    Mike Flanagan is an American filmmaker and showrunner known for his acclaimed horror films and series, including "Doctor Sleep," "The Haunting of Hill House," and "Midnight Mass."
  • D. Michael Gracey
    Michael Gracey is an Australian filmmaker and visual effects artist best known for directing the hit musical film "The Greatest Showman."
  • E. James Vanderbilt
    James Vanderbilt is an American screenwriter and producer known for penning films such as "Zodiac," "The Amazing Spider-Man," and "White House Down."
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127639bf48190800b3fa3c1527983 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:18 p.m.