Triple
T2482057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zindzi Mandela |
E55839
|
entity |
| Predicate | placeOfBirth |
P1
|
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: [Zindzi Mandela, placeOfBirth, Soweto]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soweto Context triple: [Zindzi Mandela, placeOfBirth, 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.
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.
-
C.
Mamelodi
Mamelodi is a township in the northeastern part of Pretoria, South Africa, known for its vibrant football culture and as the home of Mamelodi Sundowns F.C.
-
D.
Johannesburg, South Africa
Johannesburg, South Africa is the country’s largest city and economic hub, known for its role in the gold mining industry and as a major urban center in Gauteng province.
-
E.
Midrand
Midrand is a rapidly growing commercial and residential area in South Africa strategically located between Johannesburg and Pretoria in the province of Gauteng.
- 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_69ab49e670a88190b928e08302381710 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd163378481908b75f2f5de0e89c6 |
completed | March 7, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af1f8c02188190a7cf3e0531a66683 |
completed | March 9, 2026, 7:29 p.m. |
Created at: March 6, 2026, 9:45 p.m.