Triple
T30499389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toronto city boundary |
E776095
|
entity |
| Predicate | touches |
P5347
|
FINISHED |
| Object | Lake Ontario shoreline |
—
|
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: Lake Ontario shoreline | Statement: [Toronto city boundary, touches, Lake Ontario shoreline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: touches Context triple: [Toronto city boundary, touches, Lake Ontario shoreline]
-
A.
touchesState
Indicates that one entity is in physical contact with, or directly affects, the state or condition of another entity.
-
B.
surfaceAccess
Indicates that one entity provides a means for another entity to reach, enter, or interact with a surface or outer layer.
-
C.
handles
Indicates that one entity is responsible for dealing with, managing, or taking care of another entity or task.
-
D.
mustTouch
Indicates that the entities are required to be in direct physical contact with each other.
-
E.
interactionPoint
chosen
Indicates a specific location or moment where two or more entities come into contact or engage with each other.
- 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_69f22498c5d481908aaea89e6fab8280 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6877f55bc81908c8fce4bc1064e69 |
completed | May 2, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:14 p.m.