Triple

T17703510
Position Surface form Disambiguated ID Type / Status
Subject Santa Maria de Ripoll E441368 entity
Predicate locatedOn P40 FINISHED
Object River Ter — 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: River Ter | Statement: [Santa Maria de Ripoll, locatedOn, River Ter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: River Ter
Context triple: [Santa Maria de Ripoll, locatedOn, River Ter]
  • A. River Ter chosen
    River Ter is a river in northeastern Catalonia, Spain, that flows through the Pyrenees and the province of Girona before emptying into the Mediterranean Sea.
  • B. River Till
    River Till is a river in the Scottish Borders and northern England that flows through Northumberland before joining the River Tweed.
  • C. River Till
    River Till is a small river in Lincolnshire, England, that flows through rural farmland before joining the River Witham near Lincoln.
  • D. River Nar
    The River Nar is a small river in Norfolk, England, that flows through the countryside to join the River Great Ouse near King’s Lynn.
  • E. River Sem
    River Sem is a small river in Wiltshire, England, that flows through the Sem Valley before joining the River Nadder.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4729528b88190bd8a104f6f6d4e69 completed April 19, 2026, 6:13 a.m.
Created at: April 10, 2026, 10:05 a.m.