Triple

T11081622
Position Surface form Disambiguated ID Type / Status
Subject Libourne E262008 entity
Predicate locatedOnRiver P165 FINISHED
Object Isle River E380084 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: Isle River | Statement: [Libourne, locatedOnRiver, Isle River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isle River
Context triple: [Libourne, locatedOnRiver, Isle River]
  • A. Isle River chosen
    The Isle River is a significant waterway in southwestern France that flows through the Périgord region and the city of Périgueux before joining the Dordogne River.
  • B. Oster River
    The Oster River is a waterway in northern Ukraine that flows through the Chernihiv region before joining the Desna River.
  • C. Elm River
    Elm River is a lesser-known tributary waterway that feeds into the James River within its watershed.
  • D. Pine River
    Pine River is a Canadian waterway that serves as a tributary within the Nottawasaga River watershed in Ontario.
  • E. Pine River
    Pine River is a Canadian river that serves as a tributary of the Peace River in western Canada.
  • 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_69d6aa9983c08190b0ef61603b69feac completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d799985650819089b2c0f35a212414 completed April 9, 2026, 12:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f018324bf88190bcd2bf168b1065d3 completed April 28, 2026, 2:15 a.m.
Created at: April 8, 2026, 9:27 p.m.