Triple
T25778130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thwaites Glacier |
E649210
|
entity |
| Predicate | collapseCouldDestabilize |
P159814
|
FINISHED |
| Object | West Antarctic Ice Sheet |
—
|
NE NERFINISHED |
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: West Antarctic Ice Sheet | Statement: [Thwaites Glacier, collapseCouldDestabilize, West Antarctic Ice Sheet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collapseCouldDestabilize Context triple: [Thwaites Glacier, collapseCouldDestabilize, West Antarctic Ice Sheet]
-
A.
collapseType
Indicates the specific manner or category of failure by which something collapses or structurally gives way.
-
B.
collapsedDueTo
Indicates that one entity fell down, caved in, or structurally failed as a result of another specified cause or factor.
-
C.
collapsePeriod
Indicates the time span during which a structure, system, or entity undergoes or is subject to collapse.
-
D.
collapsedDuring
Indicates that one entity structurally failed or fell down while another specified event or process was occurring.
-
E.
collapseEvent
Indicates an event in which a structure, system, or entity suddenly falls apart, fails, or loses its integrity.
- 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_69e7ab333b508190b6d708d8d9a328ed |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fe5e7d3481908a77848582404490 |
completed | May 2, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
| PDg | Predicate description generation | batch_69f5f6b32a8881909baa0db57b80d56a |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 22, 2026, 5:35 a.m.