Triple
T10101216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Storm Lake |
E216204
|
entity |
| Predicate | hasWaterSource |
P26275
|
FINISHED |
| Object | Stony River |
E1006517
|
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: Stony River | Statement: [Mount Storm Lake, hasWaterSource, Stony River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stony River Context triple: [Mount Storm Lake, hasWaterSource, Stony River]
-
A.
Stony River
Stony River is a tributary waterway in Alaska that feeds into the Kuskokwim River system.
-
B.
Stony River
chosen
Stony River is a river in West Virginia that serves as the primary inflow and outflow for Mount Storm Lake, a reservoir used for power generation and recreation.
-
C.
Stoney River
Stoney River is a watercourse in Ireland that serves as one of the tributary rivers feeding into Lough Allen in the River Shannon system.
-
D.
Raisin River
The Raisin River is a waterway in eastern Ontario, Canada, known for flowing through rural communities such as South Glengarry before emptying into the St. Lawrence River.
-
E.
Plenty River
The Plenty River is a waterway in Victoria, Australia, that flows through Melbourne’s northeastern suburbs before joining the Yarra River.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca83d039f08190b9d10363221c69fb |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd09878f88190bcfa2c81fb10e821 |
completed | April 2, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a52daf1c81909c586e470a998073 |
completed | May 3, 2026, 1:30 a.m. |
Created at: March 30, 2026, 9:02 p.m.