Triple
T30577631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Île aux Tourtes Bridge |
E778292
|
entity |
| Predicate | alternativeRoutes |
P19868
|
FINISHED |
| Object | Autoroute 20 |
—
|
NE NERFINISHED |
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: Autoroute 20 | Statement: [Île aux Tourtes Bridge, alternativeRoutes, Autoroute 20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alternativeRoutes Context triple: [Île aux Tourtes Bridge, alternativeRoutes, Autoroute 20]
-
A.
alternativeRoute
chosen
Indicates that there exists a different path or option that can be taken instead of the primary or original route.
-
B.
tradRoutes
Indicates a relationship where one location serves as a trade route to or from another location, facilitating the movement of goods or commerce between them.
-
C.
routesFrom
Indicates that something (such as a path, connection, or communication) originates at one entity and is directed or carried from that source entity toward another.
-
D.
routeOf
Indicates that one entity is the path, course, or trajectory taken or followed by another entity (such as a vehicle, shipment, or signal).
-
E.
parallelRoute
Indicates that one route runs alongside and in the same general direction as another route without intersecting it.
- 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_69f2249f8c148190ae7eb3912cde112a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 29, 2026, 8:23 p.m.