Triple
T387724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper Peninsula of Michigan |
E8813
|
entity |
| Predicate | winterCharacteristic |
P10789
|
FINISHED |
| Object | heavy lake-effect snowfall |
—
|
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: heavy lake-effect snowfall | Statement: [Upper Peninsula of Michigan, winterCharacteristic, heavy lake-effect snowfall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winterCharacteristic Context triple: [Upper Peninsula of Michigan, winterCharacteristic, heavy lake-effect snowfall]
-
A.
snowCover
Indicates that one entity is covered by or blanketed with snow.
-
B.
requiresFrostFreeSeason
Indicates that the subject depends on a period without frost to grow, develop, or function properly.
-
C.
overwintersAs
Indicates that an organism survives through the winter in a particular life stage, form, or condition.
-
D.
season
Indicates that an entity participates in, is associated with, or occurs during a particular season or seasonal period.
-
E.
glaciationCharacteristic
Indicates that one entity is a characteristic, feature, or property associated with the process or effects of glaciation of another entity.
- F. None of above. chosen
Provenance (4 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_69a2e7f55c60819097aff65ea2ca2832 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec5828d881909e8810061c02480c |
completed | Feb. 28, 2026, 1:23 p.m. |
| PD | Predicate disambiguation | batch_69a2e967d84c8190a6b647f78d95d4e4 |
completed | Feb. 28, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69a2ea2dc3088190a2aeb4496aff3582 |
completed | Feb. 28, 2026, 1:14 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.