Triple
T18125860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oneida, New York |
E433871
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Oneida Creek |
—
|
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: Oneida Creek | Statement: [Oneida, New York, locatedOn, Oneida Creek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oneida Creek Context triple: [Oneida, New York, locatedOn, Oneida Creek]
-
A.
Oneida Creek
chosen
Oneida Creek is a stream in central New York State that drains part of the region’s watershed and empties into Oneida Lake.
-
B.
Otsquago Creek
Otsquago Creek is a stream in central New York State that flows through rural communities and farmland before emptying into the Mohawk River.
-
C.
Sauquoit Creek
Sauquoit Creek is a small stream in central New York State that flows through Oneida County and ultimately feeds into the Mohawk River.
-
D.
Coxsackie Creek
Coxsackie Creek is a small waterway in Greene County, New York, that flows into the Hudson River and lends its name to the nearby town of Coxsackie.
-
E.
Oswego Creek
Oswego Creek is a stream in Oregon that drains Oswego Lake and flows into the Willamette River.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b909e8cc81908df4cc2b8ea6d11f |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddee1efc8190b04324b98de5c9d0 |
completed | April 19, 2026, 1:51 p.m. |
Created at: April 10, 2026, 10:29 a.m.