Triple
T37101018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Builsa South District |
E918700
|
entity |
| Predicate | hasRiverOrWaterBodyNearby |
P8567
|
FINISHED |
| Object | Sissili 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: Sissili River | Statement: [Builsa South District, hasRiverOrWaterBodyNearby, Sissili River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRiverOrWaterBodyNearby Context triple: [Builsa South District, hasRiverOrWaterBodyNearby, Sissili River]
-
A.
hasNearbyWater
Indicates that one entity is located close to a body of water associated with or relevant to another entity.
-
B.
riverTypeNearby
Indicates that one entity is located near a river of a specified type or classification.
-
C.
nearbyWatercourse
chosen
Indicates that one entity is located close to or alongside a natural or artificial watercourse, such as a river, stream, or canal.
-
D.
hasNearbyRiverStructure
Indicates that a river-related structure (such as a dam, bridge, or levee) is located close to the referenced entity.
-
E.
hasNearbyWaterInfrastructure
Indicates that a location or entity is situated close to water-related infrastructure such as pipes, treatment facilities, or distribution systems.
- 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_69f76e9a48bc8190a3947508d8bca408 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd592e48cc81909d754cc6c4bd99ae |
completed | May 8, 2026, 3:31 a.m. |
| PD | Predicate disambiguation | batch_69fd58b7f9b881909dc099b28d567784 |
completed | May 8, 2026, 3:30 a.m. |
Created at: May 3, 2026, 4:14 p.m.