Triple
T142886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Washington Bridge |
E2889
|
entity |
| Predicate | tollDirection |
P3915
|
FINISHED |
| Object | eastbound |
—
|
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: eastbound | Statement: [George Washington Bridge, tollDirection, eastbound]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tollDirection Context triple: [George Washington Bridge, tollDirection, eastbound]
-
A.
hasTrafficDirection
Indicates that there is a specified flow or orientation of traffic associated with an entity (such as a road, lane, or route).
-
B.
tollingType
Indicates the specific method or basis by which a toll, fee, or charge is applied or calculated in a given context.
-
C.
tollFacilityName
Indicates the name assigned to a toll facility where tolls are collected.
-
D.
trafficDirection
chosen
Indicates the direction in which traffic is intended or allowed to move relative to a given reference point or segment.
-
E.
hasTollSegment
Indicates that a route, road, or path includes a segment where a toll must be paid.
- 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_69a2521e35c08190b28e5c9f1e3c9b59 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a2580ca15481909fa3e87d804a1b23 |
completed | Feb. 28, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69a2565559ac81909e0c4e095a7dfa27 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.