Triple
T37574438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Hampshire–Quebec border |
E934777
|
entity |
| Predicate | borderingCanadianProvince |
P180655
|
FINISHED |
| Object | Quebec |
—
|
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: Quebec | Statement: [New Hampshire–Quebec border, borderingCanadianProvince, Quebec]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderingCanadianProvince Context triple: [New Hampshire–Quebec border, borderingCanadianProvince, Quebec]
-
A.
bordersCanadianProvinceIndirectlyAcrossWater
Indicates that one region is separated from a Canadian province only by a body of water, such that they face each other across water rather than sharing a direct land border.
-
B.
inCanadianProvince
Indicates that one entity is located within, or is a part of, a specified Canadian province.
-
C.
adjacentCanadianProvince
Indicates that two entities are Canadian provinces that share a common land or maritime border.
-
D.
separatesCanadianProvince
Indicates that one entity serves as a dividing boundary between a specified Canadian province and another geographic area.
-
E.
adjacentToCanadianProvince
chosen
Indicates that one entity is directly next to or shares a border with a Canadian province.
- 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_69f76ecd99148190be327e391a70f5b6 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a000fda03948190881b7275f249768f |
completed | May 10, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_6a000f607f1881908ee750d58da91690 |
completed | May 10, 2026, 4:53 a.m. |
Created at: May 3, 2026, 4:17 p.m.