Triple

T33873876
Position Surface form Disambiguated ID Type / Status
Subject Autour de Minuit E868300 entity
Predicate Logorama P177501 FINISHED
Object won Academy Award for Best Animated Short Film 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: won Academy Award for Best Animated Short Film | Statement: [Autour de Minuit, Logorama, won Academy Award for Best Animated Short Film]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: Logorama
Context triple: [Autour de Minuit, Logorama, won Academy Award for Best Animated Short Film]
  • A. The Tourist
    Indicates a relationship where an entity is characterized as a visitor or traveler temporarily present in a place rather than a permanent resident.
  • B. محاكمة
    Indicates that a legal trial or judicial proceeding is being conducted involving the entities.
  • C. الجيل
    Indicates a generational relationship, linking entities as belonging to the same generation or specifying that one entity is a particular generation relative to another.
  • D. भूमिका
    Indicates a relationship where an entity serves, functions, or acts in a particular capacity or role with respect to another entity or context.
  • E. التأثير
    Indicates a relationship where one entity produces a change or has an influence on another entity or its state.
  • F. None of above. chosen

Provenance (4 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_69f34995029081909ede0f7df73d1a5e completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f701042bd081908bf58d12468987b6 completed May 3, 2026, 8:02 a.m.
PD Predicate disambiguation batch_69f6fc5a4f7881909324eb3c20ca96f1 completed May 3, 2026, 7:42 a.m.
PDg Predicate description generation batch_69f6fcc44af48190b95fb9e12480a85f completed May 3, 2026, 7:44 a.m.
Created at: May 1, 2026, 1:47 a.m.