Triple
T2965240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iceland Sea |
E80144
|
entity |
| Predicate | seaIce |
P4995
|
FINISHED |
| Object | multi-year sea ice presence in some years |
—
|
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: multi-year sea ice presence in some years | Statement: [Iceland Sea, seaIce, multi-year sea ice presence in some years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seaIce Context triple: [Iceland Sea, seaIce, multi-year sea ice presence in some years]
-
A.
seaIceType
Indicates the specific classification or category of sea ice associated with an entity (e.g., by age, thickness, or formation characteristics).
-
B.
seaIceMaximumExtent
Indicates the greatest spatial coverage or area that sea ice reaches during its annual or seasonal cycle.
-
C.
hasSeaIce
chosen
Indicates that one entity possesses, contains, or is covered by sea ice in relation to another context or location.
-
D.
seaIceMinimumExtent
Indicates the smallest recorded spatial coverage of sea ice over a specified period or region.
-
E.
hasSeaIceExtent
Indicates that a specified area or region possesses a measurable amount or coverage of sea ice over a given space or time.
- 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_69ad8b1341848190bd19dbf46892887d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad995a28e88190a4d6b9ef2c0d8e61 |
completed | March 8, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69ad960e71f8819088179d11248c6ed0 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.