Triple
T36568679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alaska–Yukon border |
E902052
|
entity |
| Predicate | regionType1 |
P1828
|
FINISHED |
| Object | subarctic |
—
|
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: subarctic | Statement: [Alaska–Yukon border, regionType1, subarctic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionType1 Context triple: [Alaska–Yukon border, regionType1, subarctic]
-
A.
regionType
chosen
Indicates the classification or category of a region, specifying what kind of region it is (e.g., administrative, geographic, or functional).
-
B.
regionTypeOfPlace
Indicates that a place belongs to or is categorized under a specific type of geographic or administrative region.
-
C.
regionTypeNorth
Indicates that one region is classified as the northern part or northern type relative to another region or a larger geographic context.
-
D.
regionalType
Indicates the classification of a region according to its designated type or category within a broader geographic or administrative system.
-
E.
typicalRegionType
Indicates that a region is of a characteristic or commonly occurring type for a given context or entity.
- 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_6a002103c93081908398fa5726f5fa6e |
completed | May 10, 2026, 6:09 a.m. |
| PD | Predicate disambiguation | batch_6a001fcb9fb48190a27d8f2ca983fbe6 |
completed | May 10, 2026, 6:03 a.m. |
Created at: May 3, 2026, 4:11 p.m.