Triple
T1346055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amundsen Sea |
E28572
|
entity |
| Predicate | iceShelfStatus |
P26842
|
FINISHED |
| Object | rapidly thinning ice shelves |
—
|
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: rapidly thinning ice shelves | Statement: [Amundsen Sea, iceShelfStatus, rapidly thinning ice shelves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iceShelfStatus Context triple: [Amundsen Sea, iceShelfStatus, rapidly thinning ice shelves]
-
A.
hasIcebergs
Indicates that one entity (typically a body of water or region) contains or is characterized by the presence of icebergs.
-
B.
iceRinkType
Indicates the specific kind or category of an ice rink associated with an entity (e.g., indoor, outdoor, Olympic-sized).
-
C.
freezesOver
Indicates that a liquid surface becomes solid due to low temperatures, typically forming a layer of ice over it.
-
D.
hasTypicalIceRegime
Indicates that there is a characteristic or commonly occurring pattern of ice conditions associated with the referenced entity.
-
E.
frozenIn
Indicates that one entity is immobilized or preserved in a solid, frozen state within or by 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_69a49854eb3481908c7d56b2e449a290 |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c23e84188190b0395c57dd45b62a |
completed | March 1, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69a4bef5857c81909ae984feb85a26ca |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4bf60545c8190901ccfb2cb7c4b41 |
completed | March 1, 2026, 10:36 p.m. |
Created at: March 1, 2026, 7:56 p.m.