Triple

T36955904
Position Surface form Disambiguated ID Type / Status
Subject Heavenly Sword E914186 entity
Predicate motionCaptureDirector P34445 FINISHED
Object Andy Serkis 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: Andy Serkis | Statement: [Heavenly Sword, motionCaptureDirector, Andy Serkis]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: motionCaptureDirector
Context triple: [Heavenly Sword, motionCaptureDirector, Andy Serkis]
  • A. motionCapturePerformer
    Indicates a relationship where a performer provides motion data, typically through sensors or tracking, to drive the movement of a digital character or animation.
  • B. motionCapturePioneer
    Indicates that the subject is a trailblazer or early innovator in the development or use of motion capture techniques or technology.
  • C. protagonistMotionCapture
    Indicates that motion capture data is being recorded or applied specifically to the story’s protagonist character.
  • D. movementDirector chosen
    Indicates that one entity serves as the movement director (responsible for choreographing or directing movement) for another entity, such as a performance or production.
  • E. animationDirector
    Indicates that one entity serves as the animation director responsible for overseeing and guiding the animation work of another entity.
  • 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_69f76e8b28848190abd81fe7a7374910 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fa0a7b00948190a257273d9968c5d7 completed May 5, 2026, 3:19 p.m.
PD Predicate disambiguation batch_69f9fec9c9488190ae2a349651a02782 completed May 5, 2026, 2:29 p.m.
Created at: May 3, 2026, 4:13 p.m.