Triple

T6847368
Position Surface form Disambiguated ID Type / Status
Subject River Waveney E157930 entity
Predicate flowsThrough P225 FINISHED
Object Bungay E299691 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: Bungay | Statement: [River Waveney, flowsThrough, Bungay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bungay
Context triple: [River Waveney, flowsThrough, Bungay]
  • A. Bungay chosen
    Bungay is a historic market town and civil parish situated on the River Waveney in Suffolk, England.
  • B. Caistor
    Caistor is a small historic market town in Lincolnshire, England, known for its Roman origins and Georgian architecture.
  • C. Belstead
    Belstead is a small village and civil parish located in the county of Suffolk in eastern England.
  • D. Haltwhistle
    Haltwhistle is a small town in Northumberland, England, known as a gateway to Hadrian’s Wall and the surrounding Tyne Valley countryside.
  • E. Rothbury
    Rothbury is a historic market town and civil parish in Northumberland, England, situated on the River Coquet and known as a gateway to the Northumberland National Park.
  • 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_69c6882ed4c081909dc465a7cf8838be completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d7cd0e64819097c9c211df8bce54 completed March 27, 2026, 7:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fc931d881908661483836cc059e completed March 28, 2026, 1:32 a.m.
Created at: March 27, 2026, 2:20 p.m.