Triple

T10491119
Position Surface form Disambiguated ID Type / Status
Subject AOC E247418 entity
Predicate notableExample P1503 FINISHED
Object Roquefort AOC E162264 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: Roquefort AOC | Statement: [AOC, notableExample, Roquefort AOC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roquefort AOC
Context triple: [AOC, notableExample, Roquefort AOC]
  • A. Roquefort chosen
    Roquefort is a famous French blue cheese made from sheep's milk and aged in the natural caves of Roquefort-sur-Soulzon.
  • B. Rocamadour cheese
    Rocamadour cheese is a small, soft, creamy goat’s milk cheese from France’s Lot region, prized for its delicate flavor and traditional production.
  • C. Fourme d'Ambert
    Fourme d'Ambert is a traditional French blue cheese from the Auvergne region, known for its cylindrical shape, mild creamy flavor, and protected designation of origin (PDO) status.
  • D. Langres cheese
    Langres cheese is a soft, washed-rind cow’s milk cheese from the Champagne region of France, known for its cylindrical shape with a sunken top and strong, tangy flavor.
  • E. Mont d'Or cheese
    Mont d'Or cheese is a soft, rich, washed-rind cow’s milk cheese from the Jura region of France, traditionally sold in a spruce-wood box and eaten warm and spoonable.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5097d61e08190952d4354ef1bce52 completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dca37b0881908ced885d9853bc1b completed April 10, 2026, 11:18 a.m.
Created at: April 6, 2026, 12:24 p.m.