Triple

T3023457
Position Surface form Disambiguated ID Type / Status
Subject Airport (film score) E82518 entity
Predicate partOfWorkPeriodOf P4343 FINISHED
Object late career of Alfred Newman 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: late career of Alfred Newman | Statement: [Airport (film score), partOfWorkPeriodOf, late career of Alfred Newman]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: partOfWorkPeriodOf
Context triple: [Airport (film score), partOfWorkPeriodOf, late career of Alfred Newman]
  • A. workPeriod
    Indicates the span of time during which an entity is engaged in a particular work or employment activity.
  • B. refersToPeriod chosen
    Indicates that one entity designates, references, or is associated with a specific time period or interval.
  • C. partOfWorkType
    Indicates that something is a component, subtype, or specific category within a broader type of work.
  • D. periodizedAs
    Indicates that something has been divided or organized into distinct time periods according to a particular periodization scheme.
  • E. continuedIntoPeriod
    Indicates that an action, state, or relationship that began earlier persisted without interruption into a specified later time period.
  • 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_69ad8b1fb34081908c1b873e2b7273e1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9ab8e0a48190ac79e674abd181cf completed March 8, 2026, 3:50 p.m.
PD Predicate disambiguation batch_69ad961c430c8190ac48f2e3c7e7c649 completed March 8, 2026, 3:30 p.m.
Created at: March 8, 2026, 3 p.m.