Triple

T14207574
Position Surface form Disambiguated ID Type / Status
Subject Tamworth Castle E352137 entity
Predicate locatedOn P40 FINISHED
Object River Anker E494886 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: River Anker | Statement: [Tamworth Castle, locatedOn, River Anker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Anker
Context triple: [Tamworth Castle, locatedOn, River Anker]
  • A. River Anker chosen
    The River Anker is a small river in central England that flows through Warwickshire and Staffordshire, including the town of Tamworth, before joining the River Tame.
  • B. River Alwin
    River Alwin is a small river in Northumberland, England, known for flowing through the Cheviot Hills before joining the River Coquet.
  • C. River Avich
    River Avich is a short river in Argyll and Bute, western Scotland, that flows through Glenavich before entering Loch Awe.
  • D. River Peover
    River Peover is a small river in Cheshire, England, that flows through rural countryside before joining the River Weaver.
  • E. River Anner
    River Anner is a river in County Tipperary, Ireland, known as a significant tributary contributing to the flow of the River Suir.
  • 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_69d827894ac0819097803e57f3227b23 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61f84f288190877116330bd54393 completed April 14, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69febfcd67f081909f97bcf38d814a13 completed May 9, 2026, 5:02 a.m.
Created at: April 10, 2026, 1:05 a.m.