Triple

T8911237
Position Surface form Disambiguated ID Type / Status
Subject Greenhithe for Bluewater E212186 entity
Predicate serves P98 FINISHED
Object Swanscombe E808228 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: Swanscombe | Statement: [Greenhithe for Bluewater, serves, Swanscombe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swanscombe
Context triple: [Greenhithe for Bluewater, serves, Swanscombe]
  • A. Swanscombe chosen
    Swanscombe is a town in Kent, England, known for its archaeological significance and proximity to major transport links including Ebbsfleet International railway station.
  • B. Sedlescombe
    Sedlescombe is a rural village and civil parish in East Sussex, England, known for its traditional village green and surrounding countryside.
  • C. Beckenham
    Beckenham is a suburban town in southeast London known for its residential character, green spaces, and commuter links into central London.
  • D. Westerham
    Westerham is a small historic town in Kent, England, known for its picturesque setting and associations with figures such as Winston Churchill.
  • E. Lydd
    Lydd is a small historic town in Kent, England, situated on the Romney Marsh and known for its medieval church and proximity to the English Channel.
  • 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_69ca8393b1808190bd4336787ffa2c40 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6523b9348190a7cefac9e73e2004 completed April 1, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69d190b5bb70819082b8eeb18bd5f1f6 completed April 4, 2026, 10:29 p.m.
Created at: March 30, 2026, 6:55 p.m.