Triple
T32269964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Station (Toronto) |
E824388
|
entity |
| Predicate | goTransitTerminal |
P15150
|
FINISHED |
| Object | Union Station Bus Terminal |
—
|
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: Union Station Bus Terminal | Statement: [Union Station (Toronto), goTransitTerminal, Union Station Bus Terminal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: goTransitTerminal Context triple: [Union Station (Toronto), goTransitTerminal, Union Station Bus Terminal]
-
A.
transportTerminusFor
Indicates that a location serves as the endpoint or final stop for a particular transport route or service.
-
B.
publicTransitStop
Indicates that a location serves as a designated stop or station where public transit vehicles (such as buses, trains, or trams) pick up and drop off passengers.
-
C.
terminusStation
chosen
Indicates that a station serves as the final endpoint or terminal stop for a given route or service.
-
D.
publicTransportNode
Indicates that a location functions as a node within a public transportation network, such as a stop, station, or interchange where services operate or connect.
-
E.
cityRailTerminalPeer
Indicates that two rail terminals are considered peers within the same city rail network, typically serving similar roles or being functionally equivalent.
- 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_69f3490e73588190915f282edd105772 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bc8647bc819084b1dceeb206cde5 |
completed | May 3, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:42 a.m.