Triple

T18219748
Position Surface form Disambiguated ID Type / Status
Subject Bouillon Castle E436261 entity
Predicate locatedOn P40 FINISHED
Object Semois 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: Semois River | Statement: [Bouillon Castle, locatedOn, Semois River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Semois River
Context triple: [Bouillon Castle, locatedOn, Semois River]
  • A. Semois River chosen
    The Semois River is a picturesque waterway in southern Belgium and northern France, known for winding through the rugged, forested landscapes of the Ardennes.
  • B. Aube River
    The Aube River is a major waterway in northeastern France that flows through the Champagne region before joining the Seine.
  • C. Saône River
    The Saône River is a major waterway in eastern France that flows through cities like Lyon and Dijon before joining the Rhône River.
  • D. Aude River
    The Aude River is a major river in southern France that flows through the Occitanie region before emptying into the Mediterranean Sea.
  • E. Orge River
    The Orge River is a tributary of the Seine in northern France that flows through several towns in the Île-de-France region.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e47a3b1c8190919e954089b41ae0 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.