Triple
T20768297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neumayer Glacier |
E511157
|
entity |
| Predicate | hasTypeOfIce |
P79436
|
FINISHED |
| Object | temperate glacier ice |
—
|
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: temperate glacier ice | Statement: [Neumayer Glacier, hasTypeOfIce, temperate glacier ice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfIce Context triple: [Neumayer Glacier, hasTypeOfIce, temperate glacier ice]
-
A.
hasIceType
Indicates that an entity possesses or is associated with the Ice elemental type or attribute.
-
B.
hasIceShelf
Indicates that a glacier, ice sheet, or coastline possesses an attached floating extension of ice known as an ice shelf.
-
C.
hasTypicalSeaIceType
Indicates the characteristic or commonly occurring type of sea ice associated with a given location or context.
-
D.
hasIceClass
Indicates that an object (typically a vessel or structure) is assigned a specific ice classification denoting its capability to operate in icy or ice-infested waters.
-
E.
hasIceFeature
chosen
Indicates that one entity possesses, contains, or is characterized by an ice-related feature or formation.
- 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_69e0b4ca01148190ac018e57e0cab46f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c24fa1b08190b09ab8fcb87b5c01 |
completed | April 21, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:36 p.m.