Triple

T11258827
Position Surface form Disambiguated ID Type / Status
Subject Sandton E266508 entity
Predicate hasPart P35 FINISHED
Object Illovo E712428 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: Illovo | Statement: [Sandton, hasPart, Illovo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Illovo
Context triple: [Sandton, hasPart, Illovo]
  • A. Illovo chosen
    Illovo is an affluent commercial and residential suburb in Johannesburg, South Africa, known for its corporate offices, upscale apartments, and proximity to major business and educational institutions.
  • B. Tembisa
    Tembisa is a large township in Gauteng, South Africa, situated on the East Rand and known as a densely populated residential area within the City of Ekurhuleni.
  • C. Emgesa
    Emgesa is an energy company that operates hydroelectric power facilities in Colombia.
  • D. Thohoyandou
    Thohoyandou is a town in South Africa’s Limpopo province that serves as an administrative, commercial, and educational hub for the surrounding region.
  • E. Nongoma
    Nongoma is a town in KwaZulu-Natal, South Africa, historically significant as a center of Zulu royalty and traditional leadership.
  • 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_69d6aac7953c8190b82caf9d7640fdf9 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e936cb048190b4d6fb2851ef8932 completed April 9, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4ccada158819080e49833e09f84a0 completed April 19, 2026, 12:38 p.m.
Created at: April 8, 2026, 9:31 p.m.