Triple
T7164789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diepkloof |
E167038
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Soweto |
E31807
|
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: Soweto | Statement: [Diepkloof, locatedIn, Soweto]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soweto Context triple: [Diepkloof, locatedIn, Soweto]
-
A.
Soweto
chosen
Soweto is a historically significant township in Johannesburg, South Africa, known for its central role in the struggle against apartheid and its rich urban culture.
-
B.
Hillbrow
Hillbrow is a densely populated inner-city residential neighborhood in Johannesburg, South Africa, known for its high-rise buildings, vibrant street life, and history of social and economic challenges.
-
C.
Gladysvale
Gladysvale is a fossil-bearing cave site in South Africa known for its important hominin and animal fossil discoveries within the Cradle of Humankind World Heritage area.
-
D.
Manenberg
Manenberg is a township on the Cape Flats in Cape Town, South Africa, known for its history of forced removals under apartheid and ongoing social challenges alongside strong community activism and culture.
-
E.
Bothasig
Bothasig is a residential suburb in the northern part of Cape Town, South Africa.
- 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_69c68888c10c819095e0383020225758 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e83168a08190937ff46797d94f3e |
completed | March 27, 2026, 8:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c89a543fb08190ad72c0a1f9927122 |
completed | March 29, 2026, 3:19 a.m. |
Created at: March 27, 2026, 2:47 p.m.