Triple
T9203583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delaware Memorial Bridge |
E220910
|
entity |
| Predicate | roadwayDirection |
P44884
|
FINISHED |
| Object | northbound on one span |
—
|
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: northbound on one span | Statement: [Delaware Memorial Bridge, roadwayDirection, northbound on one span]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadwayDirection Context triple: [Delaware Memorial Bridge, roadwayDirection, northbound on one span]
-
A.
hasStreetDirection
chosen
Indicates that a street or road segment is associated with a specific directional orientation (e.g., northbound, east-west).
-
B.
roadDirectionConvention
Indicates the customary rule in a place for which side of the road vehicles are expected to drive on.
-
C.
routeDirectionB
Indicates that one entity represents the direction or orientation of a route or path relative to another entity.
-
D.
transportDirection
Indicates the directional flow or route along which something is transported from an origin toward a destination.
-
E.
streetOrientedAlong
Indicates that a street is aligned or runs in the same general direction as a specified reference feature or axis.
- 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_69ca83e8e9248190862cf3e41693b310 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd944e6208190adfcc7f75197387d |
completed | April 1, 2026, 8:37 a.m. |
| PD | Predicate disambiguation | batch_69cc660af2408190ae06eb8326e1c64e |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:26 p.m.