Triple
T17137351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaaterskill Falls Trail |
E415873
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Route 23A |
E415872
|
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: Route 23A | Statement: [Kaaterskill Falls Trail, near, Route 23A]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Route 23A Context triple: [Kaaterskill Falls Trail, near, Route 23A]
-
A.
Route 23A
chosen
Route 23A is a scenic state highway in New York’s Catskill Mountains known for providing access to natural attractions such as Kaaterskill Falls.
-
B.
Route 24E
Route 24E is a historic Lisbon tram line known for its classic yellow trams and scenic journey through central neighborhoods.
-
C.
Route 24
Route 24 is a major highway in Massachusetts that provides regional north–south access through communities including Randolph.
-
D.
Route 27
Route 27 is a major north–south state highway in New Jersey that runs through several central and northern communities, serving as a key local and commuter route.
-
E.
Route 27
Route 27 is a regional roadway in Massachusetts that serves as a key connector between several suburban communities west of Boston.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2d0628081908e0160290041fe89 |
completed | April 18, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fc263508190aeeb0ea9553cebdb |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:36 a.m.