Triple
T18986742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern Province |
E464575
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | Maduru Oya |
—
|
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: Maduru Oya | Statement: [Eastern Province, hasRiver, Maduru Oya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maduru Oya Context triple: [Eastern Province, hasRiver, Maduru Oya]
-
A.
Maduru Oya
chosen
Maduru Oya is a major river in Sri Lanka known for its irrigation reservoir and surrounding national park rich in wildlife and dry-zone ecosystems.
-
B.
Maha Oya
Maha Oya is a town in Sri Lanka known for its hot springs and location within the Eastern Province.
-
C.
Galewela
Galewela is a town in Sri Lanka’s Central Province, known as an agricultural hub within the Matale District.
-
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.
Sitawaka Oya (river)
Sitawaka Oya is a river in Sri Lanka that flows through the historic Sitawaka region, contributing to its landscape and local ecosystems.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d660835c8190bedd78590b3e0a7e |
completed | April 20, 2026, 7:31 a.m. |
Created at: April 10, 2026, 12:01 p.m.