Triple
T36568645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alaska–Yukon border |
E902052
|
entity |
| Predicate | hasBorderPointWith |
P179199
|
FINISHED |
| Object | Alaska–British Columbia border |
—
|
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: Alaska–British Columbia border | Statement: [Alaska–Yukon border, hasBorderPointWith, Alaska–British Columbia border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBorderPointWith Context triple: [Alaska–Yukon border, hasBorderPointWith, Alaska–British Columbia border]
-
A.
hasBoundaryPoint
chosen
Indicates that one entity includes a point that lies on the boundary of another entity.
-
B.
liesOnBorderOf
Indicates that one entity is located along or directly adjacent to the boundary line separating it from another entity.
-
C.
hasBorderThrough
Indicates that a border between two regions or entities passes through or along a specified intermediate area, feature, or object.
-
D.
hasBorderConnection
Indicates that two regions or entities share a common boundary or are directly connected along a border.
-
E.
hasBorderElement
Indicates that one entity includes or is associated with another entity that forms part of its boundary or edge.
- 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_69f76e6416708190a9754b8c52d4e453 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe2f078c24819082ba396b56f02808 |
completed | May 8, 2026, 6:44 p.m. |
| PD | Predicate disambiguation | batch_69fe228fe1988190baf3bb34897f3dbe |
completed | May 8, 2026, 5:51 p.m. |
Created at: May 3, 2026, 4:11 p.m.