Triple
T6973550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metrorail Gauteng commuter rail |
E161655
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Randfontein |
E286175
|
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: Randfontein | Statement: [Metrorail Gauteng commuter rail, serves, Randfontein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Randfontein Context triple: [Metrorail Gauteng commuter rail, serves, Randfontein]
-
A.
Randfontein
chosen
Randfontein is a gold mining town in Gauteng, South Africa, situated west of Johannesburg on the West Rand.
-
B.
Harrismith
Harrismith is a town in the Free State province of South Africa, situated near the Drakensberg mountains and serving as an important transport and agricultural hub.
-
C.
Rustenburg
Rustenburg is a city in South Africa’s North West Province known for its mining industry and as one of the venues for the 2010 FIFA World Cup.
-
D.
Hazyview
Hazyview is a small South African town in Mpumalanga known as a gateway to Kruger National Park and the scenic attractions of the surrounding Lowveld.
-
E.
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.
- 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_69c68854a0d88190bc0bf82263f1afce |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db3aad108190b19df2d21f5ce168 |
completed | March 27, 2026, 7:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c761a6bbdc81908c96871f151db279 |
completed | March 28, 2026, 5:05 a.m. |
Created at: March 27, 2026, 2:30 p.m.