Triple
T2126471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Bakken Museum |
E46435
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | Earl Bakken |
E46435
|
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: Earl Bakken | Statement: [The Bakken Museum, founder, Earl Bakken]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Earl Bakken Context triple: [The Bakken Museum, founder, Earl Bakken]
-
A.
Earl Bakken
chosen
Earl Bakken was an American engineer and inventor best known for creating the first wearable, battery-powered pacemaker and co-founding the medical technology company Medtronic.
-
B.
George Kassabaum
George Kassabaum was an American architect and co-founder of the global design and architecture firm HOK.
-
C.
William J. Mayo
William J. Mayo was an American physician and co-founder of the Mayo Clinic, renowned for his pioneering work in modern medical practice and healthcare organization.
-
D.
B. B. Collip
B. B. Collip was a Canadian biochemist best known as a key member of the team that developed insulin as a treatment for diabetes.
-
E.
Charles H. Mayo
Charles H. Mayo was an American physician and co-founder of the Mayo Clinic, renowned for his contributions to modern medical practice and healthcare organization.
- 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_69a88a1626548190ae59a5028c3baa8e |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbb59182081908470f9be97e272c8 |
completed | March 7, 2026, 5:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5d8e61d48190af0becdc5a040cd9 |
completed | March 9, 2026, 5:41 a.m. |
Created at: March 4, 2026, 7:44 p.m.