Triple

T20689478
Position Surface form Disambiguated ID Type / Status
Subject Hertfordshire E508509 entity
Predicate borderFeature P1896 FINISHED
Object River Colne 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 Colne | Statement: [Hertfordshire, borderFeature, River Colne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Colne
Context triple: [Hertfordshire, borderFeature, River Colne]
  • A. River Colne chosen
    The River Colne is a tributary river in southern England that flows through Hertfordshire and Buckinghamshire before joining the River Thames near Staines.
  • B. River Colne
    The River Colne is a watercourse in West Yorkshire, England, flowing through Huddersfield and the Colne Valley before joining the River Calder.
  • C. River Colne
    The River Colne is a river in southeast England that flows through Essex, including the town of Colchester, before reaching the North Sea.
  • D. River Skerne
    River Skerne is a small river in County Durham, England, that flows through Darlington before joining the River Tees.
  • E. River Coln
    The River Coln is a picturesque limestone river in the Cotswolds of Gloucestershire, England, known for flowing through idyllic villages such as Bibury and contributing to classic English rural scenery.
  • 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_69e0b4c1ed408190b72dd26b1e33f8a1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c10cb5588190acb88f2c82fc593a completed April 21, 2026, 12:13 a.m.
Created at: April 16, 2026, 12:05 p.m.