Triple

T4433090
Position Surface form Disambiguated ID Type / Status
Subject Sandwell E95379 entity
Predicate formedFrom P402 FINISHED
Object Oldbury E440576 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: Oldbury | Statement: [Sandwell, formedFrom, Oldbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oldbury
Context triple: [Sandwell, formedFrom, Oldbury]
  • A. Oldbury chosen
    Oldbury is a town in the West Midlands of England that serves as the administrative centre of the Metropolitan Borough of Sandwell.
  • B. Burghfield
    Burghfield is a village and civil parish in Berkshire, England, known for its rural character and proximity to Reading.
  • C. Hordley
    Hordley is a small rural settlement located in the parish of St. Thomas in the East, Jamaica.
  • D. Gunnersbury
    Gunnersbury is a district in West London, England, known for its residential areas, parks, and transport links, including proximity to Gunnersbury Park and several major roads and rail services.
  • E. Burgh Heath
    Burgh Heath is a residential area and local community within the borough of Reigate and Banstead in Surrey, England.
  • 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_69b3453c2a0c8190926b574c90766db9 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35587bc048190aee8e0ed94b6e064 completed March 13, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6375d0d8c819095a27cdc84af9faf completed March 15, 2026, 4:36 a.m.
Created at: March 12, 2026, 11:31 p.m.