Triple
T3224795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jukskei River |
E67598
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Sandton |
E266508
|
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: Sandton | Statement: [Jukskei River, flowsThrough, Sandton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandton Context triple: [Jukskei River, flowsThrough, Sandton]
-
A.
Sandton
chosen
Sandton is an affluent commercial and financial district in Johannesburg, South Africa, known as one of the country’s primary business hubs.
-
B.
Braamfontein
Braamfontein is a central Johannesburg neighborhood known as a major cultural, educational, and judicial hub of South Africa.
-
C.
Johannesburg CBD
Johannesburg CBD is the historic commercial and financial heart of Johannesburg, characterized by dense high-rise development, major business institutions, and extensive transport links.
-
D.
Muizenberg
Muizenberg is a seaside suburb of Cape Town, South Africa, known for its popular surfing beach and colorful Victorian beach huts.
-
E.
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.
- 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_69ad858c61888190a31196310d9b30b5 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adae1c51a48190b4a395650528b5d8 |
completed | March 8, 2026, 5:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2625eaa708190b23ca6e575d664a2 |
completed | March 12, 2026, 6:51 a.m. |
Created at: March 8, 2026, 3:08 p.m.