Triple
T3882157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NOK |
E92848
|
entity |
| Predicate | usedIn |
P98
|
FINISHED |
| Object | Jan Mayen |
E27733
|
NE 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: Jan Mayen | Statement: [NOK, usedIn, Jan Mayen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Mayen Context triple: [NOK, usedIn, Jan Mayen]
-
A.
Jan Mayen
chosen
Jan Mayen is a remote volcanic island in the Arctic Ocean administered by Norway, known for its harsh climate, military and meteorological stations, and proximity to the Mid-Atlantic Ridge.
-
B.
Saronde Island
Saronde Island is a small tropical island in Gorontalo, Indonesia, known for its white-sand beaches, clear turquoise waters, and popular snorkeling and diving spots.
-
C.
Bear Island
Bear Island is one of the Apostle Islands in Lake Superior, known for its rugged natural shoreline and forested, relatively undeveloped landscape within the Apostle Islands region of northern Wisconsin.
-
D.
Nansen Island
Nansen Island is a polar island named in honor of Norwegian explorer, scientist, and humanitarian Fridtjof Nansen.
-
E.
Nørvøya
Nørvøya is a coastal island in western Norway that forms part of the urban area of the town of Ålesund.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed9697de0819087c2559295ff3d12 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeec8d5c1c8190906294177f3ad49e |
completed | March 9, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b533788a70819089d028cee84a7e87 |
completed | March 14, 2026, 10:07 a.m. |
Created at: March 9, 2026, 3:20 p.m.