Triple
T36588969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sun Kosi River |
E902611
|
entity |
| Predicate | countryDownstreamSystem |
P113283
|
FINISHED |
| Object | India |
E1124
|
NE 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: India | Statement: [Sun Kosi River, countryDownstreamSystem, India]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryDownstreamSystem Context triple: [Sun Kosi River, countryDownstreamSystem, India]
-
A.
downstreamCountry
Indicates that one country is located downstream along a shared river or watercourse relative to another country.
-
B.
countryDownstreamBasin
chosen
Indicates that one country lies within the downstream portion of a river basin relative to another country or reference point.
-
C.
downstreamFacility
Indicates that one facility is located or operates downstream from another facility within a flow or process network.
-
D.
countryBorderDownstream
Indicates that one country lies downstream along a shared river or watercourse from another country, relative to the direction of water flow.
-
E.
downstreamSettlement
Indicates that one settlement is located downstream from another along the same watercourse, in the direction of the water flow.
- F. None of above.
Provenance (4 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_69f76e6592e88190bac4eb00a46e9df9 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0316136a14819085bb88563d5abc42 |
completed | May 12, 2026, 11:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39f90e2bf88190ad0b92137c3f961c |
completed | June 23, 2026, 3:10 a.m. |
| PD | Predicate disambiguation | batch_6a03158a962c81909f17d58197f6ba00 |
completed | May 12, 2026, 11:56 a.m. |
Created at: May 3, 2026, 4:11 p.m.