Triple

T19092973
Position Surface form Disambiguated ID Type / Status
Subject Sarah Gadon E467333 entity
Predicate hasWorkedWith P9615 FINISHED
Object Brandon Cronenberg 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: Brandon Cronenberg | Statement: [Sarah Gadon, hasWorkedWith, Brandon Cronenberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brandon Cronenberg
Context triple: [Sarah Gadon, hasWorkedWith, Brandon Cronenberg]
  • A. Brandon Cronenberg chosen
    Brandon Cronenberg is a Canadian filmmaker known for his visually striking, psychologically intense science fiction and horror films that often explore themes of identity, technology, and bodily transformation.
  • B. David Cronenberg
    David Cronenberg is a Canadian filmmaker renowned for his influential body horror and psychological thriller films, such as "The Fly," "Videodrome," and "Crash."
  • C. Vincenzo Natali
    Vincenzo Natali is a Canadian filmmaker best known for directing the cult science fiction horror film "Cube" and other visually inventive genre movies.
  • D. Cronenberg
    Cronenberg is a former independent town in western Germany that is now a district of the city of Wuppertal in North Rhine-Westphalia.
  • E. Christophe Gans
    Christophe Gans is a French film director best known for his visually stylized adaptations of genre works such as "Silent Hill" and "Brotherhood of the Wolf."
  • 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e34cf5e481908e1f180dacd5602f completed April 20, 2026, 8:26 a.m.
Created at: April 10, 2026, 12:04 p.m.