Triple
T28238702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saptakoshi River |
E711957
|
entity |
| Predicate | KoshiBarrageLocation |
P26898
|
FINISHED |
| Object | Sunsari District |
—
|
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: Sunsari District | Statement: [Saptakoshi River, KoshiBarrageLocation, Sunsari District]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: KoshiBarrageLocation Context triple: [Saptakoshi River, KoshiBarrageLocation, Sunsari District]
-
A.
barrageLocation
chosen
Indicates the location where a barrage (such as an artillery or concentrated attack) is directed or occurs.
-
B.
Gitwangak Battle Hill
Indicates a historical or geographic relationship in which events, conflicts, or activities are associated with the specific site known as Gitwangak Battle Hill.
-
C.
prominenceRelativeToKibo
Indicates how prominent or noticeable one entity is in comparison to Kibo.
-
D.
waterfallLocation
Indicates the spatial location or geographic area where a waterfall is situated.
-
E.
riverLocation
Indicates that a river is located in, passes through, or is geographically associated with a specified place or region.
- 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_69efb51ece308190b8c269a057e36652 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f643c3aab88190842770d1bc058c07 |
completed | May 2, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 10:56 p.m.