Triple
T2963792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breeze Airways |
E80111
|
entity |
| Predicate | routeStrategy |
P12563
|
FINISHED |
| Object | point-to-point network |
—
|
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: point-to-point network | Statement: [Breeze Airways, routeStrategy, point-to-point network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routeStrategy Context triple: [Breeze Airways, routeStrategy, point-to-point network]
-
A.
route
Indicates that one entity serves as a path or course used to travel or move between locations associated with another entity.
-
B.
routeSegment
Indicates a specific portion of a larger route that directly connects two points or locations within that route.
-
C.
routeStructure
Indicates the structural or organizational relationship between a route and its constituent segments, paths, or connections.
-
D.
routingBasis
chosen
Indicates the principle or criterion used to determine how something is directed, routed, or assigned among possible paths or destinations.
-
E.
routeExtension
Indicates that an existing route is extended beyond its original endpoint to cover additional segments or destinations.
- 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_69ad8b1341848190bd19dbf46892887d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9957602c819089b673966fd619e0 |
completed | March 8, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69ad960e71f8819088179d11248c6ed0 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.