Triple

T5933815
Position Surface form Disambiguated ID Type / Status
Subject Michelin E131996 entity
Predicate notableWork P4 FINISHED
Object Michelin Guide E555269 NE 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: Michelin Guide | Statement: [Michelin, notableWork, Michelin Guide]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelin Guide
Context triple: [Michelin, notableWork, Michelin Guide]
  • A. Michelin Guide chosen
    The Michelin Guide is an influential series of restaurant and hotel guides best known for awarding coveted Michelin stars that signify exceptional culinary quality.
  • B. Michelin Stars
    Michelin Stars are prestigious culinary awards that recognize and rank exceptional restaurants for the quality of their cuisine, service, and overall dining experience.
  • C. Tour d’Argent
    Tour d’Argent is a historic tower that forms part of the former royal palace complex on the Île de la Cité in Paris, now known as the Conciergerie.
  • D. Michelin Travel Guides
    Michelin Travel Guides are a series of travel publications by the Michelin company, best known for their detailed maps, tourist information, and influential hotel and restaurant recommendations.
  • E. Halles de Lyon Paul Bocuse
    Halles de Lyon Paul Bocuse is a renowned indoor food market in Lyon, France, celebrated for its high-quality gourmet products and association with legendary chef Paul Bocuse.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69c0085c55dc8190aa90e242c956e2fa completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0389f6fc881909527b928838ffcdd completed March 22, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3affd748190a37e3cc60e58d6a6 completed March 23, 2026, 6:54 a.m.
Created at: March 22, 2026, 4 p.m.