Triple
T26818086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Last Glacial Period |
E675171
|
entity |
| Predicate | iceSheetsCovered |
P161503
|
FINISHED |
| Object | large parts of northern Asia |
—
|
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: large parts of northern Asia | Statement: [Last Glacial Period, iceSheetsCovered, large parts of northern Asia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iceSheetsCovered Context triple: [Last Glacial Period, iceSheetsCovered, large parts of northern Asia]
-
A.
iceSheetsCovered
chosen
Indicates that ice sheets extended over and covered a particular area or surface.
-
B.
seaIceType
Indicates the specific classification or category of sea ice associated with an entity (e.g., by age, thickness, or formation characteristics).
-
C.
hasSeaIce
Indicates that one entity possesses, contains, or is covered by sea ice in relation to another context or location.
-
D.
summitIceCover
Indicates the extent or presence of ice covering the summit of a geographic feature.
-
E.
snowCover
Indicates that one entity is covered by or blanketed with snow.
- 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_69eee9b6b28481909332f83eb17e5170 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620debeb48190b7db395fb86cf8d9 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 4:53 a.m.