Triple
T24352883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bank of Toronto building at Yonge and King |
E613841
|
entity |
| Predicate | streetCorner |
P17242
|
FINISHED |
| Object | Yonge Street |
—
|
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: Yonge Street | Statement: [Bank of Toronto building at Yonge and King, streetCorner, Yonge Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: streetCorner Context triple: [Bank of Toronto building at Yonge and King, streetCorner, Yonge Street]
-
A.
streetLocation
chosen
Indicates that one entity is located on, along, or at a specific street associated with the other entity.
-
B.
streetSet
Indicates that a particular street belongs to, or is included within, a specified set or collection of streets.
-
C.
betweenStreets
Indicates that one location is situated between two specified streets, typically along a road segment bounded by those streets.
-
D.
crossesStreet
Indicates that an entity moves from one side of a street to the other, traversing the street’s width.
-
E.
locatedBetweenStreets
Indicates that something is situated between two specified streets, with its position bounded or defined by those streets.
- 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_69e2d7ddd29481909e7f539a6072bd71 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2934732908190a50e69f492a5dc7a |
completed | April 29, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:59 a.m.