Triple
T22420640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kotmale Oya |
E554235
|
entity |
| Predicate | mouth |
P407
|
FINISHED |
| Object | Mahaweli River |
—
|
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: Mahaweli River | Statement: [Kotmale Oya, mouth, Mahaweli River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mahaweli River Context triple: [Kotmale Oya, mouth, Mahaweli River]
-
A.
Mahaweli River
chosen
The Mahaweli River is the longest river in Sri Lanka, playing a crucial role in the country’s irrigation, agriculture, and hydroelectric power generation.
-
B.
Seethawaka Ganga
Seethawaka Ganga is a river in Sri Lanka that flows through the historic Seethawaka region and contributes to the Kelani River system.
-
C.
Karnaphuli River
The Karnaphuli River is a major river in southeastern Bangladesh that flows through the port city of Chittagong before emptying into the Bay of Bengal.
-
D.
Kala Oya
Kala Oya is one of Sri Lanka’s major rivers, flowing through the country’s dry zone and supporting irrigation, agriculture, and local ecosystems.
-
E.
Mahaweli Ganga
Mahaweli Ganga is the longest river in Sri Lanka, playing a crucial role in the country’s irrigation, agriculture, and hydroelectric power generation.
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1594a58508190b41fd16c8de5f8b4 |
completed | April 29, 2026, 1:05 a.m. |
Created at: April 16, 2026, 8:46 p.m.