Triple
T21200122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antarctic ice shelves |
E522431
|
entity |
| Predicate | observedChange |
P143528
|
FINISHED |
| Object | widespread thinning in West Antarctica |
—
|
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: widespread thinning in West Antarctica | Statement: [Antarctic ice shelves, observedChange, widespread thinning in West Antarctica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observedChange Context triple: [Antarctic ice shelves, observedChange, widespread thinning in West Antarctica]
-
A.
observedFor
Indicates that one entity is monitored, watched, or examined over a period of time for the benefit or analysis of another entity.
-
B.
observedWhen
Indicates that one entity is observed or recorded at a specific time or under particular temporal conditions.
-
C.
behaviorObserved
Indicates that a particular behavior or action has been witnessed, recorded, or detected in relation to an entity or context.
-
D.
observedWith
Indicates that two or more entities are seen, detected, or recorded together in the same context, event, or observation.
-
E.
observedEvent
Indicates that an entity has perceived, detected, or recorded the occurrence of a particular event.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7342fe3a08190b7ed2cadf60091a8 |
completed | April 21, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69e5f6094e3c81909ee9699e00d371f7 |
completed | April 20, 2026, 9:46 a.m. |
| PDg | Predicate description generation | batch_69e5fa92a2448190896c022dd27511ad |
completed | April 20, 2026, 10:06 a.m. |
Created at: April 16, 2026, 3:18 p.m.