Triple
T8017729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northwest Angle |
E186659
|
entity |
| Predicate | isOnlyLandBorderOf |
P43880
|
FINISHED |
| Object | contiguous United States with Manitoba |
—
|
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: contiguous United States with Manitoba | Statement: [Northwest Angle, isOnlyLandBorderOf, contiguous United States with Manitoba]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOnlyLandBorderOf Context triple: [Northwest Angle, isOnlyLandBorderOf, contiguous United States with Manitoba]
-
A.
hasBorderWithNonSovereignEntity
chosen
Indicates that one entity shares a land or maritime border with a political or territorial unit that is not fully sovereign.
-
B.
borderedBy
Indicates that one entity shares a common boundary or edge with another entity.
-
C.
countryBordering
Indicates that one country shares a land or maritime boundary directly with another country.
-
D.
provinceBordering
Indicates that two provinces share a common boundary or border with each other.
-
E.
longestLandBorderWith
Indicates that two entities share a land border and that this border is the longest land border for at least one of the entities.
- 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_69ca82ac7fc081909b1398cf025423af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3df4f1b8819089a8b67f136bce9a |
completed | March 31, 2026, 3:22 a.m. |
| PD | Predicate disambiguation | batch_69cb048c9f488190b4fb8917a9c21bc5 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:20 p.m.