Triple

T6340718
Position Surface form Disambiguated ID Type / Status
Subject Morbihan E142615 entity
Predicate contains P35 FINISHED
Object Belle-Île E293895 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: Belle-Île | Statement: [Morbihan, contains, Belle-Île]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Belle-Île
Context triple: [Morbihan, contains, Belle-Île]
  • A. Belle-Île chosen
    Belle-Île is a scenic French Atlantic island off the coast of Brittany, known for its rugged cliffs, beaches, and maritime heritage.
  • B. Île de Ré
    Île de Ré is a popular Atlantic island off the west coast of France, known for its sandy beaches, salt marshes, and charming villages connected to the mainland by a long bridge.
  • C. Bréhat archipelago
    The Bréhat archipelago is a picturesque cluster of small granite islands off the northern coast of France, renowned for its mild microclimate, lush vegetation, and car-free main island popular with tourists.
  • D. Île de Nantes
    Île de Nantes is a large river island in the Loire at the heart of Nantes, France, known for its major urban redevelopment and creative, cultural attractions.
  • E. Île d’Yeu
    Île d’Yeu is a small French Atlantic island off the Vendée coast, known for its rugged coastline, sandy beaches, and historic fortifications.
  • 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_69c008d5ab108190b346c465696824a9 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0674311388190bb069a07a7ff60ef completed March 22, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640aceaf88190bff029848444e23a completed March 27, 2026, 8:32 a.m.
Created at: March 22, 2026, 4:30 p.m.