Triple

T16214417
Position Surface form Disambiguated ID Type / Status
Subject Madeleines de Commercy E393547 entity
Predicate hasServingOccasion P14787 FINISHED
Object snack 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: snack | Statement: [Madeleines de Commercy, hasServingOccasion, snack]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasServingOccasion
Context triple: [Madeleines de Commercy, hasServingOccasion, snack]
  • A. servingOccasion chosen
    Indicates the occasion, event, or context during which something (typically food or drink) is served.
  • B. hasOccasionType
    Indicates that an occasion, event, or happening is classified as being of a particular type or category.
  • C. hasServingCustom
    Indicates that an entity follows or applies a particular custom, style, or convention in how something (such as food, drink, or service) is served.
  • D. servedDuring
    Indicates that one entity held a role, position, or performed a function within the time period defined by another entity.
  • E. eatenOnOccasion
    Indicates that one entity is consumed or eaten by another only at certain times or under specific circumstances, rather than regularly or habitually.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227f393e08190be93400d754f0a2d completed April 17, 2026, 12:30 p.m.
PD Predicate disambiguation batch_69e219e94a448190b73a4e6aa374eb4a completed April 17, 2026, 11:30 a.m.
Created at: April 10, 2026, 5:03 a.m.