Triple
T18729243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Forest Hills station |
E457986
|
entity |
| Predicate | hasPedestrianConnections |
P60843
|
FINISHED |
| Object | overpasses and underpasses |
—
|
LITERAL 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: overpasses and underpasses | Statement: [Forest Hills station, hasPedestrianConnections, overpasses and underpasses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPedestrianConnections Context triple: [Forest Hills station, hasPedestrianConnections, overpasses and underpasses]
-
A.
hasPedestrianAccessTo
Indicates that a location or area can be reached or entered safely and directly by people on foot.
-
B.
hasPedestrianOverpass
chosen
Indicates that there exists a pedestrian overpass connecting or spanning parts of the referenced location or infrastructure.
-
C.
hasPedestrianSections
Indicates that an object (such as a route, road, or area) includes one or more sections specifically designated for pedestrian use.
-
D.
hasPedestrianFunction
Indicates that an entity serves a role, purpose, or function specifically related to pedestrians or pedestrian use.
-
E.
hasPedestrianArea
Indicates that a location or zone includes a designated area intended for pedestrian use only or primarily.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56d7660488190b4f70db963d05ef6 |
completed | April 20, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:50 a.m.