Triple

T8620811
Position Surface form Disambiguated ID Type / Status
Subject Peter Andrews E204157 entity
Predicate creditType P41710 FINISHED
Object on-screen cinematography credit 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: on-screen cinematography credit | Statement: [Peter Andrews, creditType, on-screen cinematography credit]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: creditType
Context triple: [Peter Andrews, creditType, on-screen cinematography credit]
  • A. cardType
    Indicates the classification or category assigned to a card within a given system or context.
  • B. creditFlexibility
    Indicates that one party allows adaptable or negotiable credit terms, limits, or repayment conditions for another party.
  • C. includesCreditCategory
    Indicates that one entity contains or encompasses a specific credit-related category within its defined set or structure.
  • D. collateralType
    Indicates the kind or category of collateral associated with an obligation, agreement, or financial exposure.
  • E. requiresCreditAs chosen
    Indicates that one entity must be credited or acknowledged in a specified manner or role in relation to 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_69ca832ceab8819096e4a9f546695079 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc5730309081909a9a0256c9bf5f8f completed March 31, 2026, 11:22 p.m.
PD Predicate disambiguation batch_69cc455906f8819082edd79cb4a1cf28 completed March 31, 2026, 10:06 p.m.
Created at: March 30, 2026, 6:26 p.m.