Triple
T18989230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York State Thruway Exit 21 |
E464638
|
entity |
| Predicate | accesses |
P1985
|
FINISHED |
| Object | NY 23 |
—
|
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: NY 23 | Statement: [New York State Thruway Exit 21, accesses, NY 23]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NY 23 Context triple: [New York State Thruway Exit 21, accesses, NY 23]
-
A.
NY 23
chosen
NY 23 is a state highway in New York that runs east–west across the state, connecting rural communities, small cities, and major routes in the Catskills and beyond.
-
B.
NY 3
NY 3 is a state highway in northern New York that runs east–west between the Adirondack Mountains and the Lake Ontario shoreline.
-
C.
NY 2
NY 2 is a state highway in New York that runs through the Capital District, connecting the city of Troy to the Massachusetts state line.
-
D.
NY 30
NY 30 is a north–south state highway in New York that runs through the Adirondack Mountains and Mohawk Valley, connecting rural communities across the eastern-central part of the state.
-
E.
NY 33
NY 33 is a state highway in New York that serves as a major urban arterial route through Buffalo and its eastern suburbs.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d66272388190850a7e5dec165a01 |
completed | April 20, 2026, 7:31 a.m. |
Created at: April 10, 2026, 12:01 p.m.