Triple

T3491358
Position Surface form Disambiguated ID Type / Status
Subject French Riviera E73737 entity
Predicate hasCity P316 FINISHED
Object Grasse E389045 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: Grasse | Statement: [French Riviera, hasCity, Grasse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grasse
Context triple: [French Riviera, hasCity, Grasse]
  • A. Grasse chosen
    Grasse is a town in southeastern France renowned as the world’s perfume capital and a historic center of the fragrance industry.
  • B. Aix-en-Provence
    Aix-en-Provence is a historic and picturesque city in southern France, renowned for its Provençal charm, fountains, and as the hometown of painter Paul Cézanne.
  • C. Bourg-la-Reine
    Bourg-la-Reine is a residential suburb in the southern outskirts of Paris, France, known for its convenient commuter access to the capital and its quiet, small-town atmosphere.
  • D. Brunoy
    Brunoy is a suburban commune in the southeastern outskirts of Paris, France, known for its residential character and location along the Yerres River.
  • E. Garches
    Garches is a suburban commune in the western outskirts of Paris, France, known for its residential character and proximity to major Parisian business districts.
  • 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_69ad85cca8d4819088494e9f3340fab5 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbbaa720c8190af47b052cc66c225 completed March 8, 2026, 6:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69b6279969388190a808a3c5995df2c5 completed March 15, 2026, 3:29 a.m.
Created at: March 8, 2026, 3:18 p.m.