Triple
T19967296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunyani River |
E479970
|
entity |
| Predicate | hasReservoir |
P1025
|
FINISHED |
| Object | Manyame Dam |
—
|
NE NERFINISHED |
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: Manyame Dam | Statement: [Hunyani River, hasReservoir, Manyame Dam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manyame Dam Context triple: [Hunyani River, hasReservoir, Manyame Dam]
-
A.
Manyame Dam
chosen
Manyame Dam is a major reservoir in Zimbabwe that supplies water for irrigation, urban use, and hydroelectric power generation along the Manyame River.
-
B.
Yonki Dam
Yonki Dam is a major hydroelectric dam in Papua New Guinea that supplies significant power to the country’s highlands region.
-
C.
Surobi Dam
Surobi Dam is a hydroelectric and irrigation dam located on the Kabul River in eastern Afghanistan.
-
D.
Jounama Dam
Jounama Dam is a major rockfill embankment dam in New South Wales, Australia, forming part of the Snowy Mountains Scheme’s hydroelectric and water management system.
-
E.
Lodoyo Dam
Lodoyo Dam is a water control and irrigation structure located on the Brantas River in East Java, Indonesia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65bc5e41881908c1e8867820f1c0c |
completed | April 20, 2026, 5 p.m. |
Created at: April 10, 2026, 1:54 p.m.