Triple
T29284921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NY 301 |
E742482
|
entity |
| Predicate | westernTerminusNearbyFeature |
P4246
|
FINISHED |
| Object | Hudson River |
—
|
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: Hudson River | Statement: [NY 301, westernTerminusNearbyFeature, Hudson River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: westernTerminusNearbyFeature Context triple: [NY 301, westernTerminusNearbyFeature, Hudson River]
-
A.
westernTerminusNear
chosen
Indicates that the western endpoint of one entity is located close to another entity.
-
B.
westernTerminusDetail
Indicates the specific endpoint location or characteristics associated with the western terminus of a route or linear feature.
-
C.
westernTerminusConnectsTo
Indicates that the western endpoint or terminus of one route, line, or path is directly connected to another specified route, line, or location.
-
D.
westernTerminusCrosses
Indicates that the western endpoint of a route, line, or path intersects or passes over another feature or boundary.
-
E.
locatedWestOf
Indicates that one entity is positioned geographically to the west of another entity.
- 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_69f09121ed8c8190b4cb27be3619c262 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f665191d888190b4ab2c4bbd7725cb |
completed | May 2, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f663362c008190a22afed262f1e426 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 12:57 p.m.