Triple

T5990380
Position Surface form Disambiguated ID Type / Status
Subject E. Vincent Harris E133332 entity
Predicate workLocation P7 FINISHED
Object Wakefield E53034 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: Wakefield | Statement: [E. Vincent Harris, workLocation, Wakefield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wakefield
Context triple: [E. Vincent Harris, workLocation, Wakefield]
  • A. Wakefield chosen
    Wakefield is a historic cathedral city in West Yorkshire, Northern England, known for its medieval heritage and role as an administrative and commercial center in the region.
  • B. Wakefield
    Wakefield is a suburban town in Middlesex County, Massachusetts, known for its commuter access to Boston and its scenic Lake Quannapowitt.
  • C. Wakefield
    Wakefield is a picturesque village in western Quebec, Canada, known for its historic covered bridge, arts community, and scenic setting along the Gatineau River.
  • D. Wakefield
    Wakefield is a small rural township in New Zealand’s Tasman District, located southwest of Nelson and serving as a local service and farming community.
  • E. Bradford
    Bradford is a town in Ontario, Canada, serving as the main urban centre of the municipality of Bradford West Gwillimbury.
  • 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_69c0087010d081908bb8142342d63330 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04dc8ab648190beb1bc141796894e completed March 22, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1413ca5f88190b0dab30bde04af4c completed March 23, 2026, 1:33 p.m.
Created at: March 22, 2026, 4:05 p.m.