Triple
T33945802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivy Lea, Ontario |
E870285
|
entity |
| Predicate | bridgeAccessVia |
P177955
|
FINISHED |
| Object | Thousand Islands Bridge |
—
|
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: Thousand Islands Bridge | Statement: [Ivy Lea, Ontario, bridgeAccessVia, Thousand Islands Bridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bridgeAccessVia Context triple: [Ivy Lea, Ontario, bridgeAccessVia, Thousand Islands Bridge]
-
A.
bridgeUsed
Indicates that a bridge is utilized or traversed by an entity to cross between two locations or points.
-
B.
bridgeFeature
Indicates that one entity functions as a structural or functional feature of a bridge associated with another entity.
-
C.
bridgeLocation
Indicates the specific place or area where a bridge is situated or spans.
-
D.
bridgeConnectsVia
Indicates that a bridge serves as the connecting structure or route between two locations or entities via a specified path or medium.
-
E.
bridgeComponent
Indicates that one entity functions as a structural or functional component of a bridge associated with another entity.
- F. None of above. chosen
Provenance (4 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69f7064d37388190993b2a7305a02b9f |
completed | May 3, 2026, 8:24 a.m. |
Created at: May 1, 2026, 1:49 a.m.