Triple

T22152223
Position Surface form Disambiguated ID Type / Status
Subject Fortifications of Bayonne E547441 entity
Predicate locatedOn P40 FINISHED
Object Adour River — NE NERFINISHED

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: Adour River | Statement: [Fortifications of Bayonne, locatedOn, Adour River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Adour River
Context triple: [Fortifications of Bayonne, locatedOn, Adour River]
  • A. Adour chosen
    Adour is a major river in southwestern France that flows from the Pyrenees to the Atlantic Ocean, passing through cities such as Tarbes and Bayonne.
  • B. Aude River
    The Aude River is a major river in southern France that flows through the Occitanie region before emptying into the Mediterranean Sea.
  • C. Aure River
    The Aure River is a small waterway in Normandy, northwestern France, that flows through the historic town of Bayeux before joining the Vire River.
  • D. Têt River
    The Têt River is a coastal river in southern France that flows through the Pyrénées-Orientales department before emptying into the Mediterranean Sea.
  • E. Gave de Pau River
    The Gave de Pau River is a river in southwestern France that flows through the Pyrenees and the city of Pau before joining the Adour.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e3b52088190ad5df386d01eb2fb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129f4b05c8190a824f55804f6d4d5 completed April 28, 2026, 9:43 p.m.
Created at: April 16, 2026, 8:33 p.m.