Triple

T7396406
Position Surface form Disambiguated ID Type / Status
Subject Deadpool 2 E170631 entity
Predicate castMember P1668 FINISHED
Object Julian Dennison E235692 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: Julian Dennison | Statement: [Deadpool 2, castMember, Julian Dennison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julian Dennison
Context triple: [Deadpool 2, castMember, Julian Dennison]
  • A. Julian Dennison chosen
    Julian Dennison is a New Zealand actor best known for his breakout role in "Hunt for the Wilderpeople" and his performance in "Deadpool 2."
  • B. Julian Richards
    Julian Richards is a British film director and screenwriter known for his work in independent horror and thriller cinema.
  • C. Julian Reid
    Julian Reid is a relatively obscure individual whose specific public notability is not clearly established from the available information.
  • D. Julian Stevens
    Julian Stevens is a television producer best known for his executive production work on high-profile drama series such as *The North Water*.
  • E. Julian Clarke
    Julian Clarke is a Canadian film editor known for his work on major feature films, including the science fiction movie "Elysium."
  • 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_69c68a5f04188190ac266569c9280347 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f248f79c819094b1d1e2c3d511d1 completed March 27, 2026, 9:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c845e96a2c819099decde57a57bec3 completed March 28, 2026, 9:19 p.m.
Created at: March 27, 2026, 3:09 p.m.