Triple
T23237921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahaweli Ganga |
E581353
|
entity |
| Predicate | hasDam |
P8736
|
FINISHED |
| Object | Kotmale 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: Kotmale Dam | Statement: [Mahaweli Ganga, hasDam, Kotmale Dam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kotmale Dam Context triple: [Mahaweli Ganga, hasDam, Kotmale Dam]
-
A.
Kotmale Dam
chosen
Kotmale Dam is a major hydroelectric and irrigation dam in Sri Lanka, forming part of the Mahaweli Development Programme and creating the Kotmale Reservoir.
-
B.
Navilatirtha Dam
Navilatirtha Dam is a major irrigation and water management structure built across the Malaprabha River in Karnataka, India.
-
C.
Somasila Dam
Somasila Dam is a major irrigation and water storage structure built across the Penna River in Andhra Pradesh, India.
-
D.
Bhushi Dam
Bhushi Dam is a popular masonry dam and scenic picnic spot near Lonavala in Maharashtra, India, known for its cascading water steps and monsoon-time crowds.
-
E.
Gajanur Dam
Gajanur Dam is a scenic reservoir and popular tourist spot in Karnataka, India, known for its lush surroundings and role in irrigation and water management near Shivamogga.
- 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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192ea590c81908cd677d89f67d49f |
completed | April 29, 2026, 5:11 a.m. |
Created at: April 17, 2026, 4:09 p.m.