Triple
T2090470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bransfield Strait |
E32655
|
entity |
| Predicate | hasNearbyResearchStation |
P5648
|
FINISHED |
| Object | King George Island research stations |
—
|
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: King George Island research stations | Statement: [Bransfield Strait, hasNearbyResearchStation, King George Island research stations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyResearchStation Context triple: [Bransfield Strait, hasNearbyResearchStation, King George Island research stations]
-
A.
containsResearchStation
Indicates that one entity geographically includes or hosts a research station within its boundaries.
-
B.
nearestResearchStation
Indicates that one research station is the closest in distance to a given location or entity compared to all other research stations.
-
C.
hasNearbyBase
Indicates that one entity has a base or facility located in close physical proximity to another entity or location.
-
D.
hasResearchCentersIn
Indicates that an entity maintains or operates research centers located within a specified place or region.
-
E.
hasNearbyFacility
chosen
Indicates that one entity is located close to or in the vicinity of a particular facility.
- 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_69a885eba0708190999696a45cbec816 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abba7443448190a2642769d0b5fb93 |
completed | March 7, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69abb7b4356881909217c42ccb8bb1ed |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.