Triple

T3610012
Position Surface form Disambiguated ID Type / Status
Subject Chinon E76462 entity
Predicate river P165 FINISHED
Object Vienne River E252485 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: Vienne River | Statement: [Chinon, river, Vienne River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vienne River
Context triple: [Chinon, river, Vienne River]
  • A. Vienne River chosen
    The Vienne River is a major waterway in west-central France that flows through cities such as Limoges before joining the Loire.
  • B. Chiers River
    The Chiers River is a tributary of the Meuse that flows through Luxembourg, Belgium, and northeastern France, passing industrial towns such as Longwy along its course.
  • C. Doux River
    The Doux River is a watercourse in southeastern France that flows through the historical Vivarais region of the Ardèche.
  • D. Indre River
    The Indre River is a tributary of the Loire in central France, known for flowing through the historic Touraine region and its picturesque rural landscapes.
  • E. Bienne River
    The Bienne River is a watercourse in eastern France that flows through the Jura region before joining the Ain River.
  • 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_69ad85da0ba481908b3b48c69efe2b98 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc22b824c8190a85b36185d4957bb completed March 8, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b503dbed588190abe9ca45b1ff68f8 completed March 14, 2026, 6:44 a.m.
Created at: March 8, 2026, 3:23 p.m.