Triple

T8841919
Position Surface form Disambiguated ID Type / Status
Subject When We Were Young E210406 entity
Predicate mainCharacterAgePerspective P1924 FINISHED
Object adult reflecting on youth 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: adult reflecting on youth | Statement: [When We Were Young, mainCharacterAgePerspective, adult reflecting on youth]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mainCharacterAgePerspective
Context triple: [When We Were Young, mainCharacterAgePerspective, adult reflecting on youth]
  • A. protagonistAge
    Indicates the age of the main character or central figure in a narrative or scenario.
  • B. ageDuringNarration
    Indicates that an entity has a specified age at the time when the described narrative or event is taking place.
  • C. narrativePerspective chosen
    Indicates the point of view or vantage from which a narrative is told, specifying the relationship between the storyteller and the events being described.
  • D. representedAgeLevel
    Indicates that one entity corresponds to, or is categorized under, a particular age level or age group.
  • E. portraysYoungerVersionOfCharacterFrom
    Indicates that one character is depicted as a younger version of another character from a specified source.
  • 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_69ca838967bc8190b46c3c80a2887ea4 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60876c6c8190b1b490e447e1cf4b completed April 1, 2026, 12:02 a.m.
PD Predicate disambiguation batch_69cc5c25b874819084c9ba391703e066 completed March 31, 2026, 11:43 p.m.
Created at: March 30, 2026, 6:48 p.m.