Triple

T20151665
Position Surface form Disambiguated ID Type / Status
Subject Inanda, near Durban E491447 entity
Predicate locatedNear P294 FINISHED
Object Durban 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: Durban | Statement: [Inanda, near Durban, locatedNear, Durban]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durban
Context triple: [Inanda, near Durban, locatedNear, Durban]
  • A. Durban chosen
    Durban is a major coastal city in South Africa known for its busy port, subtropical climate, and significant Indian community.
  • B. Cape Town
    Cape Town is a major coastal city in South Africa known for its iconic Table Mountain, diverse culture, and role as the country’s legislative capital.
  • C. Pietermaritzburg
    Pietermaritzburg is a major city in South Africa’s KwaZulu-Natal province, historically significant as a colonial administrative center and now known for its Victorian architecture and role as a regional economic and educational hub.
  • D. Durban–Cape Town
    Durban–Cape Town is a major domestic air route in South Africa connecting the coastal cities of Durban and Cape Town.
  • E. Durban–Port Elizabeth
    Durban–Port Elizabeth is a regional air route in South Africa connecting the coastal cities of Durban and Port Elizabeth.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667dc34e081908e42e4c1bde26170 completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:33 p.m.