Triple

T15327625
Position Surface form Disambiguated ID Type / Status
Subject Occasu E366451 entity
Predicate occursInContext P34621 FINISHED
Object heraldry 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: heraldry | Statement: [Occasu, occursInContext, heraldry]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: occursInContext
Context triple: [Occasu, occursInContext, heraldry]
  • A. isRaisedInContextOf
    Indicates that an entity is brought up, discussed, or introduced within a particular situational, thematic, or conversational context.
  • B. namedInContextOf chosen
    Indicates that an entity is mentioned or identified specifically within a particular context, situation, or frame of reference.
  • C. occursFor
    Indicates that an event, process, or condition takes place in relation to, or on behalf of, a particular entity or context.
  • D. performedInContextOf
    Indicates that an action or event was carried out within, and is meaningfully related to, a specific situational, procedural, or environmental context.
  • E. implementedInContextOf
    Indicates that something (such as a method, feature, or process) is carried out or realized within a particular surrounding situation, framework, or set of conditions.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dffd6f88190a0f031ee90c6a7d2 completed April 16, 2026, 1:40 a.m.
PD Predicate disambiguation batch_69deca9659f48190b8661df223ce5078 completed April 14, 2026, 11:15 p.m.
Created at: April 10, 2026, 3:16 a.m.