Triple

T4419316
Position Surface form Disambiguated ID Type / Status
Subject King Kong (2005 film) E95057 entity
Predicate portraysCharacterViaMotionCapture P37849 FINISHED
Object Andy Serkis as King Kong LITERAL 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: Andy Serkis as King Kong | Statement: [King Kong (2005 film), portraysCharacterViaMotionCapture, Andy Serkis as King Kong]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: portraysCharacterViaMotionCapture
Context triple: [King Kong (2005 film), portraysCharacterViaMotionCapture, Andy Serkis as King Kong]
  • A. protagonistMotionCapture
    Indicates that motion capture data is being recorded or applied specifically to the story’s protagonist character.
  • B. portraysActorAs
    Indicates that one entity depicts or represents an actor in a particular role, character, or manner.
  • C. portrayedVia chosen
    Indicates that one entity is represented, depicted, or expressed through a particular medium, method, or channel.
  • D. portrayalRecognition
    Indicates that one entity recognizes or identifies another entity as a portrayal or representation of a particular subject or character.
  • E. portraysFictionalEntity
    Indicates that one entity depicts, represents, or plays the role of a fictional character or figure.
  • F. None of above.

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_69b3453a36908190b95a79a297ca083c completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3551e7c6c819090fa5dfb5ac58e4c completed March 13, 2026, 12:06 a.m.
PD Predicate disambiguation batch_69b34f5d0c54819085c08533bb58030a completed March 12, 2026, 11:42 p.m.
Created at: March 12, 2026, 11:29 p.m.