Triple

T23465743
Position Surface form Disambiguated ID Type / Status
Subject Dimension Data Pro-Am E569097 entity
Predicate location P40 FINISHED
Object George, South Africa NE NERFINISHED

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: George, South Africa | Statement: [Dimension Data Pro-Am, location, George, South Africa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George, South Africa
Context triple: [Dimension Data Pro-Am, location, George, South Africa]
  • A. George, Western Cape chosen
    George, Western Cape is a major town along South Africa’s Garden Route, known for its forestry industry, golf courses, and role as a regional transport and commercial hub.
  • B. Johannesburg–George
    Johannesburg–George is a domestic air route in South Africa connecting the major city of Johannesburg with the coastal town of George.
  • C. Cape Town–George
    Cape Town–George is a domestic air route in South Africa connecting the coastal city of Cape Town with the town of George along the Garden Route.
  • D. Transkei, South Africa
    Transkei, South Africa was a former bantustan in the southeastern part of the country, historically designated for Xhosa-speaking people during the apartheid era.
  • E. Vereeniging, South Africa
    Vereeniging is an industrial city in South Africa’s Gauteng province, historically known for its steel and coal industries and its role in the country’s mining and manufacturing economy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6faaf8c8190b4fd191c54e1acea completed April 29, 2026, 6:36 a.m.
Created at: April 17, 2026, 5:54 p.m.