Triple
T12603040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kasai region |
E300904
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Kasai River |
E1034147
|
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: Kasai River | Statement: [Kasai region, river, Kasai River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kasai River Context triple: [Kasai region, river, Kasai River]
-
A.
Kasai River
chosen
The Kasai River is a major tributary of the Congo River in central Africa, flowing through Angola and the Democratic Republic of the Congo and serving as an important waterway for the surrounding regions.
-
B.
Beni River
The Beni River is a major waterway in northern Bolivia that flows through the Amazon Basin, supporting rich biodiversity and local communities along its course.
-
C.
Kunda River
Kunda River is a regional river flowing through the Khargone district in the Indian state of Madhya Pradesh.
-
D.
Assa River
The Assa River is a mountain river in the North Caucasus that flows through parts of Georgia and Russia before joining the Terek River.
-
E.
Assa River
The Assa River is a waterway in the North Caucasus region that flows through parts of Russia and Georgia before joining the Sunzha 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954e6e20481908bca684c4b497c48 |
completed | April 10, 2026, 7:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f72658fa6c81909b9785d710c418e0 |
completed | May 3, 2026, 10:41 a.m. |
Created at: April 9, 2026, 5:10 p.m.