Triple
T2875350
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crocodile River (Limpopo) |
E56864
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object | Jukskei River |
E67598
|
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: Jukskei River | Statement: [Crocodile River (Limpopo), hasTributary, Jukskei River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jukskei River Context triple: [Crocodile River (Limpopo), hasTributary, Jukskei River]
-
A.
Jukskei River
chosen
The Jukskei River is a significant urban river in South Africa’s Gauteng province, flowing through Johannesburg and its surrounding areas and playing a key role in the region’s drainage system.
-
B.
Atrek River
The Atrek River is a transboundary river in northeastern Iran and southern Turkmenistan that flows westward along their border before emptying into the southeastern Caspian Sea.
-
C.
Mangfall River
The Mangfall River is a river in Bavaria, Germany, that drains the Tegernsee and flows northward to join the Inn River.
-
D.
Klip River
The Klip River is a river in KwaZulu-Natal, South Africa, that flows through the town of Ladysmith and forms part of the Tugela River basin.
-
E.
Notwane River
The Notwane River is a significant river in southern Africa that flows through Botswana and parts of South Africa before joining the Limpopo River.
- 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_69ab4a4ced288190ab6d3e062d10f7f6 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abe004a64481908f1897d9054a7368 |
completed | March 7, 2026, 8:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4dae657ec81909e8a99e4ccd95bfc |
completed | March 14, 2026, 3:49 a.m. |
Created at: March 6, 2026, 10:03 p.m.