Triple
T34873560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toronto–Windsor |
E1005817
|
entity |
| Predicate | connectsToBorderCity |
P145819
|
FINISHED |
| Object | Windsor |
—
|
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: Windsor | Statement: [Toronto–Windsor, connectsToBorderCity, Windsor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsToBorderCity Context triple: [Toronto–Windsor, connectsToBorderCity, Windsor]
-
A.
hasBorderCity
Indicates that one location is a city situated on or very near the border of another geographic or political region.
-
B.
cityIsBorderCity
Indicates that a city is located on or near a boundary between two regions, countries, or administrative areas.
-
C.
connectsToCountryBorder
Indicates that one entity is directly adjacent to and touches the border of a specified country.
-
D.
connectsBorderCities
chosen
Indicates a relationship where a route, infrastructure, or boundary directly links two or more cities that lie on or near a shared border.
-
E.
isBorderTownBetween
Indicates that a town is located on or near the boundary separating two specified regions, serving as a border settlement between them.
- 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_69f76dbde1c08190a24e7f9beb564c8d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff70ecc1a481909571b18d56d982b8 |
completed | May 9, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69ff70322a3c8190837840ea42cd3093 |
completed | May 9, 2026, 5:34 p.m. |
Created at: May 3, 2026, 4 p.m.