Triple
T22823751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalu River |
E565294
|
entity |
| Predicate | hasFloodPlain |
P14914
|
FINISHED |
| Object | Kalutara floodplain |
—
|
LITERAL 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: Kalutara floodplain | Statement: [Kalu River, hasFloodPlain, Kalutara floodplain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFloodPlain Context triple: [Kalu River, hasFloodPlain, Kalutara floodplain]
-
A.
hasFloodplain
chosen
Indicates that an area or location lies within the floodplain associated with a particular water body or flooding source.
-
B.
hasFloodplains
Indicates that an area or region includes land that is subject to flooding, typically adjacent to a river or water body.
-
C.
hasFloodplainType
Indicates that an area or location is associated with a specific type or classification of floodplain.
-
D.
hasFloodplainUse
Indicates that a floodplain area is being used or designated for a particular purpose or activity.
-
E.
hasFloodRisk
Indicates that an entity is exposed to a potential or expected risk of flooding under certain conditions.
- F. None of above.
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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17dd2005081909baef070124eb839 |
completed | April 29, 2026, 3:41 a.m. |
| PD | Predicate disambiguation | batch_69eed2d117088190acbfe130d84f8627 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:34 p.m.