Triple

T18727038
Position Surface form Disambiguated ID Type / Status
Subject Birstall E457926 entity
Predicate near P350 FINISHED
Object River Soar 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 Soar | Statement: [Birstall, near, River Soar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Soar
Context triple: [Birstall, near, River Soar]
  • A. River Soar chosen
    The River Soar is a major river in central England that flows through Leicestershire and the city of Leicester before joining the River Trent.
  • B. River Sowe
    The River Sowe is a tributary of the River Avon in the West Midlands of England, flowing through Warwickshire and the Coventry area.
  • C. River Leam
    The River Leam is a small river in central England that flows through the town of Leamington Spa before joining the River Avon.
  • D. Aire River
    Aire River is a watercourse in the canton of Geneva, Switzerland, known for flowing through rural landscapes and forming part of the local municipal boundaries.
  • E. River Lud
    The River Lud is a small river in Lincolnshire, England, that flows through the market town of Louth before joining the River Witham system.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d74bd9881908cd314e68327c402 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:50 a.m.