Triple
T3190503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vaal River |
E66809
|
entity |
| Predicate | suppliesWaterTo |
P4102
|
FINISHED |
| Object | Vanderbijlpark |
E58237
|
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: Vanderbijlpark | Statement: [Vaal River, suppliesWaterTo, Vanderbijlpark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vanderbijlpark Context triple: [Vaal River, suppliesWaterTo, Vanderbijlpark]
-
A.
Vanderbijlpark
chosen
Vanderbijlpark is an industrial city in South Africa known for its large steel production facilities and location on the Vaal River.
-
B.
Roodepoort
Roodepoort is a suburban city on the western side of Johannesburg in South Africa, known for its residential areas, shopping centers, and proximity to the Witwatersrand hills.
-
C.
Krugersdorp
Krugersdorp is a historic mining town in South Africa known for its gold deposits and location on the West Rand of the Gauteng province.
-
D.
Randjespark
Randjespark is a commercial and residential suburb in the Midrand area of Johannesburg, South Africa, known for its business parks and proximity to major transport routes.
-
E.
Ermelo
Ermelo is a key agricultural and transport hub town located in South Africa’s Mpumalanga province.
- 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada6e7d0d081908b1c36bb909a58bf |
completed | March 8, 2026, 4:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b262126fa08190b7dd620159e3ed96 |
completed | March 12, 2026, 6:49 a.m. |
Created at: March 8, 2026, 3:07 p.m.