Triple

T12009573
Position Surface form Disambiguated ID Type / Status
Subject Hamish McColl E285870 entity
Predicate collaboratedWith P435 FINISHED
Object Paul King E311062 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: Paul King | Statement: [Hamish McColl, collaboratedWith, Paul King]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul King
Context triple: [Hamish McColl, collaboratedWith, Paul King]
  • A. Paul King chosen
    Paul King is a British filmmaker and screenwriter best known for directing the critically acclaimed Paddington films.
  • B. Phil Lord
    Phil Lord is an American filmmaker, writer, and producer best known for his inventive, comedic work on projects like The Lego Movie and the 21 Jump Street and Spider-Verse films.
  • C. Joe Cornish
    Joe Cornish is a British filmmaker, comedian, and writer best known for his work on the sci-fi film "Attack the Block" and his collaborations with Edgar Wright.
  • D. Michael Arndt
    Michael Arndt is an Academy Award–winning American screenwriter known for acclaimed films such as Little Miss Sunshine and Toy Story 3.
  • E. Jordan Vogt-Roberts
    Jordan Vogt-Roberts is an American film director best known for helming the 2017 blockbuster monster movie "Kong: Skull Island."
  • 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_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903d61a4c81909e6cb6500b61df94 completed April 10, 2026, 2:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69f48b24f0c481909afd288d4f57d3b6 completed May 1, 2026, 11:14 a.m.
Created at: April 8, 2026, 9:46 p.m.