Triple

T17933766
Position Surface form Disambiguated ID Type / Status
Subject Sherborne railway station E448399 entity
Predicate servedPlace P3936 FINISHED
Object Sherborne 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: Sherborne | Statement: [Sherborne railway station, servedPlace, Sherborne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sherborne
Context triple: [Sherborne railway station, servedPlace, Sherborne]
  • A. Sherborne
    Sherborne is a small rural village in West Oxfordshire, England, known for its traditional Cotswold stone buildings and picturesque countryside setting.
  • B. Sherborne chosen
    Sherborne is a historic market town in southwest England renowned for its medieval abbey, castles, and well-preserved architecture.
  • C. Malmesbury
    Malmesbury is a historic market town in Wiltshire, England, renowned for its ancient abbey and status as one of the oldest continually inhabited towns in the country.
  • D. Malmesbury
    Malmesbury is a historic agricultural town in South Africa’s Western Cape, known as a service and commercial hub for the surrounding Swartland grain and wine-farming region.
  • E. Cranborne
    Cranborne is a historic village in Dorset, England, known for its medieval church, traditional architecture, and rural countryside setting.
  • 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4a5547b7881909dc41bb7dd34194f completed April 19, 2026, 9:50 a.m.
Created at: April 10, 2026, 10:21 a.m.