Triple

T5807600
Position Surface form Disambiguated ID Type / Status
Subject River Dart E128782 entity
Predicate nearbyTown P3883 FINISHED
Object Totnes E219507 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: Totnes | Statement: [River Dart, nearbyTown, Totnes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Totnes
Context triple: [River Dart, nearbyTown, Totnes]
  • A. Totnes chosen
    Totnes is a historic market town and former parliamentary borough in Devon, England, known for its rich heritage and independent, bohemian character.
  • B. Winscombe
    Winscombe is a large village and civil parish in North Somerset, England, known for its rural setting and community amenities.
  • C. Southwold
    Southwold is a residential neighbourhood within the town of Bicester in Oxfordshire, England.
  • D. Southwold
    Southwold is a small seaside town and popular tourist resort on the North Sea coast of Suffolk, England, known for its pier, beach huts, and historic lighthouse.
  • E. Honiton
    Honiton is a market town in East Devon, England, historically known for its lace-making and situated on key transport routes in the region.
  • 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_69c0084788848190bcf71f6bc5d71597 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02b17417081908779741b9bfbb720 completed March 22, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a17f77fc8190b2ad6f6c45d96e43 completed March 23, 2026, 2:12 a.m.
Created at: March 22, 2026, 3:52 p.m.