Triple
T15572065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westchester Creek |
E374269
|
entity |
| Predicate | mouth |
P407
|
FINISHED |
| Object | East River |
E473
|
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: East River | Statement: [Westchester Creek, mouth, East River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: East River Context triple: [Westchester Creek, mouth, East River]
-
A.
East River
chosen
The East River is a tidal strait in New York City that separates Manhattan from Brooklyn and Queens and serves as a major waterway spanned by several iconic bridges.
-
B.
East River
The East River is a tributary waterway in the Appalachian region of the United States that flows through southern West Virginia and into Virginia.
-
C.
East River
The East River is a mountain river in Gunnison County, Colorado, that flows through the Elk Mountains and joins the Taylor River to form the Gunnison River.
-
D.
East River
East River is a rural locality within Western Australia’s Shire of Ravensthorpe, characterized by its agricultural landscape and proximity to natural bushland.
-
E.
East River
East River is a tributary of the Fox River in northeastern Wisconsin, flowing through Brown and Calumet counties before emptying into Green Bay.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e2025888190a2b6240296bba13e |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f30e48881908b30a71796fe0d72 |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:10 a.m.