Triple
T16167358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croton Falls station |
E392339
|
entity |
| Predicate | connectingRoad |
P54298
|
FINISHED |
| Object | New York State Route 22 |
—
|
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: New York State Route 22 | Statement: [Croton Falls station, connectingRoad, New York State Route 22]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectingRoad Context triple: [Croton Falls station, connectingRoad, New York State Route 22]
-
A.
linkedByRoadTo
Indicates that two locations are directly connected to each other by a road suitable for travel.
-
B.
roadTerminusOf
Indicates that a road ends at, or has its terminal point at, the referenced location or route.
-
C.
roadConnectivityStatus
Indicates the current state of whether and how well two locations are connected by a road network.
-
D.
hasConnectingRoadNumber
chosen
Indicates that there exists a road connection between two locations or road segments identified by a specific road number.
-
E.
hasConnectingStreet
Indicates that two locations are linked by a street that directly connects them.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21eb3ec4c81908d4e5c0f39a85900 |
completed | April 17, 2026, 11:51 a.m. |
| PD | Predicate disambiguation | batch_69e1828abb608190a99d86bce1d77de2 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:02 a.m.