Triple

T20582295
Position Surface form Disambiguated ID Type / Status
Subject Driffield Navigation E505687 entity
Predicate connects P390 FINISHED
Object Driffield 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: Driffield | Statement: [Driffield Navigation, connects, Driffield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Driffield
Context triple: [Driffield Navigation, connects, Driffield]
  • A. Driffield chosen
    Driffield is a market town in the East Riding of Yorkshire, England, known historically as the "Capital of the Wolds" for its role as a commercial and agricultural centre for the surrounding countryside.
  • B. Mirfield
    Mirfield is a small town in West Yorkshire, England, known for its position on major rail routes and its historic textile industry.
  • C. Waldringfield
    Waldringfield is a small riverside village in eastern England known for its scenic setting on the River Deben and sailing activities.
  • D. Kildwick
    Kildwick is a small historic village in North Yorkshire, England, situated near the River Aire and known for its ancient church and scenic rural setting.
  • E. Austerfield
    Austerfield is a small village in South Yorkshire, England, notable for its historic church and connections to early English history.
  • 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_69e0b4b9669c8190b8e81fc72817d42c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a90f7e34819086b1745dcd53ba25 completed April 20, 2026, 10:30 p.m.
Created at: April 16, 2026, 11:40 a.m.