Triple

T13653924
Position Surface form Disambiguated ID Type / Status
Subject University of the Western Cape E326808 entity
Predicate city P40 FINISHED
Object Bellville E326809 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: Bellville | Statement: [University of the Western Cape, city, Bellville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bellville
Context triple: [University of the Western Cape, city, Bellville]
  • A. Bellville chosen
    Bellville is a suburb of Cape Town in South Africa, known as an educational and residential hub that includes the campus of the University of the Western Cape.
  • B. Atteridgeville
    Atteridgeville is a township in the western part of Pretoria, South Africa, known for its rich political history and vibrant local culture.
  • C. Erindale
    Erindale is a residential neighbourhood in the city of Mississauga, Ontario, known for its parks, schools, and proximity to the Credit River.
  • D. Caledon
    Caledon is a small town in South Africa’s Western Cape province, known for its hot springs, surrounding farmlands, and proximity to the Overberg region.
  • E. Caledon
    Caledon is a largely rural town in southern Ontario, Canada, known for its scenic landscapes and inclusion within the Greater Toronto Area.
  • 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc60ace048190a4b92310ba272bd1 completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78affa3c481909dba71e2ce9f44c1 completed May 3, 2026, 5:50 p.m.
Created at: April 9, 2026, 9:52 p.m.