Triple
T19658713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurontario Street |
E472018
|
entity |
| Predicate | transitModePlanned |
P28705
|
FINISHED |
| Object | light rail transit |
—
|
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: light rail transit | Statement: [Hurontario Street, transitModePlanned, light rail transit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transitModePlanned Context triple: [Hurontario Street, transitModePlanned, light rail transit]
-
A.
plannedTransit
Indicates that a transit or trip has been scheduled or arranged to occur, but has not yet taken place.
-
B.
transportPlanned
Indicates that an arrangement has been made for something or someone to be transported from one place to another.
-
C.
transportationPlanned
Indicates that an arrangement has been made for someone or something to be transported from one place to another.
-
D.
publicTransitMode
chosen
Indicates the type of public transportation (e.g., bus, train, subway) used or associated with a given trip or segment.
-
E.
rideTypePlanned
Indicates that a specific type or category of ride has been scheduled or intended in advance.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641485ce481908b3860fa5e3a9f6e |
completed | April 20, 2026, 3:07 p.m. |
| PD | Predicate disambiguation | batch_69e514e941008190898d978d7bde91e4 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.