Triple
T23096821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sverdrup Islands |
E575912
|
entity |
| Predicate | expeditionShip |
P35089
|
FINISHED |
| Object | Fram |
—
|
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: Fram | Statement: [Sverdrup Islands, expeditionShip, Fram]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fram Context triple: [Sverdrup Islands, expeditionShip, Fram]
-
A.
Fram
chosen
Fram was a pioneering Norwegian polar exploration ship, specially designed for Arctic and Antarctic expeditions led by explorers such as Fridtjof Nansen and Roald Amundsen.
-
B.
Rače–Fram
Rače–Fram is a settlement and municipality in northeastern Slovenia, known for its location near Maribor and its mix of rural and suburban character.
-
C.
Fisker
Fisker is a Danish surname most notably associated with architect Kay Fisker and, more broadly, with several prominent Danish figures in design, architecture, and the arts.
-
D.
Framm
Framm is the surname of Josh Framm, the young protagonist from the "Air Bud" film series.
-
E.
Nemschoff
Nemschoff is a furniture manufacturer best known for its durable, design-focused healthcare and institutional seating and casegoods.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de522e48190a37e6c2fda2de465 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:57 p.m.