Triple
T22514968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viggo Widerøe |
E556617
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Viggo Widerøe |
—
|
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: Viggo Widerøe | Statement: [Viggo Widerøe, name, Viggo Widerøe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Viggo Widerøe Context triple: [Viggo Widerøe, name, Viggo Widerøe]
-
A.
Viggo Widerøe
chosen
Viggo Widerøe was a Norwegian aviation pioneer and entrepreneur best known for founding the regional airline Widerøe.
-
B.
Arne Wilhelmsen
Arne Wilhelmsen was a Norwegian shipping magnate and co-founder who played a key role in building Royal Caribbean into one of the world’s largest cruise lines.
-
C.
Knud Jeppesen
Knud Jeppesen was a Danish musicologist and composer renowned for his influential work on Renaissance counterpoint and the music of Palestrina.
-
D.
Holger Jeppesen
Holger Jeppesen was a notable figure significant enough in his community or field to have Jeppesen Stadium named in his honor.
-
E.
Gunnar Sønsteby
Gunnar Sønsteby was a highly decorated Norwegian resistance fighter during World War II, renowned for his sabotage operations and leadership against the German occupation.
- 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15e2c3098819098a553133cc9515b |
completed | April 29, 2026, 1:26 a.m. |
Created at: April 16, 2026, 8:50 p.m.