Triple

T10224282
Position Surface form Disambiguated ID Type / Status
Subject Patrick Kenzie – Casey Affleck E242660 entity
Predicate cameraFocus P31 FINISHED
Object character-driven narrative 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: character-driven narrative | Statement: [Patrick Kenzie – Casey Affleck, cameraFocus, character-driven narrative]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: cameraFocus
Context triple: [Patrick Kenzie – Casey Affleck, cameraFocus, character-driven narrative]
  • A. autofocusPoints
    Indicates the relationship between a camera (or imaging device) and the specific focus points it can automatically select or use for focusing.
  • B. focusOf
    Indicates that one entity is the primary subject, target, or center of attention, activity, or interest for another entity.
  • C. typicalBackFocus
    Indicates a relationship where attention, emphasis, or focus is characteristically directed toward the back or rear part of something.
  • D. focusesOn chosen
    Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
  • E. telescopeFocus
    Indicates that one entity adjusts or sets the focal point of a telescope relative to another entity or target.
  • 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d3aa84a9ac819093d551005a1c8f3d completed April 6, 2026, 12:43 p.m.
PD Predicate disambiguation batch_69d3955f61f88190b8d37ff645cd44d3 completed April 6, 2026, 11:13 a.m.
Created at: April 6, 2026, 11:11 a.m.