Triple

T15465002
Position Surface form Disambiguated ID Type / Status
Subject Ditton Marsh E372008 entity
Predicate locatedNear P294 FINISHED
Object Thames Ditton E248173 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: Thames Ditton | Statement: [Ditton Marsh, locatedNear, Thames Ditton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thames Ditton
Context triple: [Ditton Marsh, locatedNear, Thames Ditton]
  • A. Thames Ditton chosen
    Thames Ditton is a suburban riverside village in Surrey, England, known for its picturesque setting on the River Thames and proximity to southwest London.
  • B. Teddington
    Teddington is a suburban town in southwest London, England, known for its riverside location on the Thames and proximity to several royal parks.
  • C. Walton-on-Thames
    Walton-on-Thames is a suburban town on the River Thames in southeast England, known for its commuter links to London and riverside amenities.
  • D. Merstham
    Merstham is a village and suburb in Surrey, England, known for its historic centre and proximity to the town of Redhill.
  • E. Datchet
    Datchet is a riverside village and civil parish in Berkshire, England, situated on the River Thames near Windsor.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f680cec8190836a5ec841dee224 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff677ef27c81909fd160205b71ca55 completed May 9, 2026, 4:57 p.m.
Created at: April 10, 2026, 3:33 a.m.