Triple
T23363591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whillans Ice Stream |
E593249
|
entity |
| Predicate | hasResearchStationNearby |
P111661
|
FINISHED |
| Object | field camps on Ross Ice Shelf region |
—
|
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: field camps on Ross Ice Shelf region | Statement: [Whillans Ice Stream, hasResearchStationNearby, field camps on Ross Ice Shelf region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasResearchStationNearby Context triple: [Whillans Ice Stream, hasResearchStationNearby, field camps on Ross Ice Shelf region]
-
A.
hasNearbyResearchStations
chosen
Indicates that one entity has research stations located in close geographical proximity to it.
-
B.
containsResearchStation
Indicates that one entity geographically includes or hosts a research station within its boundaries.
-
C.
nearbyResearchStationFormerName
Indicates that a nearby research station previously had a different name, specifying that former name.
-
D.
hasPermanentResearchStations
Indicates that one entity maintains long-term, continuously operating research facilities within the domain or territory of another entity.
-
E.
nearestResearchStation
Indicates that one research station is the closest in distance to a given location or entity compared to all other research stations.
- 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aac4248190a4663ed12aed6856 |
completed | April 29, 2026, 6:09 a.m. |
| PD | Predicate disambiguation | batch_69f061c7aaa48190a58ce93f87155ffc |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:31 p.m.