Triple

T8238040
Position Surface form Disambiguated ID Type / Status
Subject Pretoria Campus E192461 entity
Predicate name P16 FINISHED
Object Pretoria Campus E192461 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: Pretoria Campus | Statement: [Pretoria Campus, name, Pretoria Campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pretoria Campus
Context triple: [Pretoria Campus, name, Pretoria Campus]
  • A. Pretoria Campus chosen
    Pretoria Campus is the main urban campus of the Tshwane University of Technology, located in South Africa’s administrative capital city.
  • B. Mamelodi Campus
    Mamelodi Campus is a satellite campus of the University of Pretoria located in the Mamelodi township, focused on access and extended academic programmes.
  • C. Bloemfontein campus
    Bloemfontein campus is the primary campus of the University of the Orange Free State, located in the city of Bloemfontein, South Africa.
  • D. Soweto Campus
    Soweto Campus is a University of Johannesburg campus located in Soweto, serving as a key higher-education hub for the surrounding community.
  • E. Braamfontein Campus
    Braamfontein Campus is the main urban campus of the University of the Witwatersrand in Johannesburg, known for its academic, administrative, and student life facilities.
  • 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_69ca82dc8f148190a2c75a98501a7b91 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb783a8cf48190bf85394fd3bd79e2 completed March 31, 2026, 7:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc6b591d081909e1fb450508197f2 completed April 2, 2026, 1:30 a.m.
Created at: March 30, 2026, 5:47 p.m.