Triple

T1225627
Position Surface form Disambiguated ID Type / Status
Subject Norfolk E26320 entity
Predicate borders P224 FINISHED
Object Suffolk E64456 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: Suffolk | Statement: [Norfolk, borders, Suffolk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suffolk
Context triple: [Norfolk, borders, Suffolk]
  • A. Suffolk chosen
    Suffolk is a historic rural county in eastern England known for its coastal towns, medieval villages, and agricultural landscapes.
  • B. Essex
    Essex is a county in the east of England, known for its mix of rural landscapes, historic towns, and proximity to London.
  • C. Sussex
    Sussex is a traditional British dual-purpose chicken breed valued for both its meat and egg production.
  • D. Hampshire
    Hampshire is a county on England’s south coast known for its historic cities, naval and military heritage, and mix of rural countryside and coastal areas.
  • E. West Suffolk
    West Suffolk is a local government district in the county of Suffolk, England, encompassing towns such as Bury St Edmunds and Newmarket.
  • 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be39908481908cca21aaf0828415 completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0fc0a32ec819089d3e4f7d7b86c89 completed March 11, 2026, 5:22 a.m.
Created at: March 1, 2026, 7:47 p.m.