Triple
T24334183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rutford Ice Stream |
E613331
|
entity |
| Predicate | channelsIceFrom |
P48630
|
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: [Rutford Ice Stream, channelsIceFrom, West Antarctic Ice Sheet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: channelsIceFrom Context triple: [Rutford Ice Stream, channelsIceFrom, West Antarctic Ice Sheet]
-
A.
iceFeature
Indicates a relationship where a geographic or environmental feature is composed of, covered by, or characterized by ice.
-
B.
iceCapability
Indicates that an entity has the ability or functional capacity to produce, manage, or utilize ice.
-
C.
receivesIcebergsFrom
Indicates that one entity is the source or destination in a process where it obtains or is supplied with icebergs from another entity.
-
D.
channels
Indicates that one entity serves as a medium, route, or conduit through which another entity is directed, transmitted, or delivered.
-
E.
hasIceSource
chosen
Indicates that one entity serves as the origin or provider of ice for another entity.
- 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_69e2d7dcc5a08190b53691130d56cbc4 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292f381b08190b529a765a5d5e89b |
completed | April 29, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_69f287ad30048190b3ad3613486f277f |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:56 a.m.