Triple
T22386924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kon-Tiki raft |
E553418
|
entity |
| Predicate | crewMember |
P2094
|
FINISHED |
| Object | Bengt Danielsson |
—
|
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: Bengt Danielsson | Statement: [Kon-Tiki raft, crewMember, Bengt Danielsson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bengt Danielsson Context triple: [Kon-Tiki raft, crewMember, Bengt Danielsson]
-
A.
Bengt Danielsson
chosen
Bengt Danielsson was a Swedish anthropologist and writer best known for joining Thor Heyerdahl’s 1947 Kon-Tiki expedition across the Pacific Ocean.
-
B.
Bengt Falk
Bengt Falk was a Swedish nobleman and official who was executed during the 1600 Linköping Bloodbath, a major political purge ordered by King Charles IX.
-
C.
Bengt Nilsson
Bengt Nilsson is a Swedish high jumper who won the gold medal at the 1954 European Championships and briefly held the world record in the event.
-
D.
Yngve Lindström
Yngve Lindström is a person notable enough to be recognized as a significant bearer of the surname Lindström.
-
E.
Göran Lennmarker
Göran Lennmarker is a Swedish politician known for his long service in the Riksdag and his work on foreign affairs and security policy.
- 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158304bcc81908c4c5db09a246bcc |
completed | April 29, 2026, 1 a.m. |
Created at: April 16, 2026, 8:45 p.m.