Triple
T20824113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bornholm Art Museum |
E512651
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Fogh & Følner |
—
|
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: Fogh & Følner | Statement: [Bornholm Art Museum, architect, Fogh & Følner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fogh & Følner Context triple: [Bornholm Art Museum, architect, Fogh & Følner]
-
A.
Fogh & Følner
chosen
Fogh & Følner is a Danish architectural firm known for its modern, context-sensitive designs, including the acclaimed Bornholm Art Museum in Denmark.
-
B.
Per Frandsen
Per Frandsen is a former Danish professional footballer and midfielder best known for his influential spell at Bolton Wanderers in the 1990s.
-
C.
Dryfoos
Dryfoos is a surname most notably associated with Orvil E. Dryfoos, a former publisher of The New York Times.
-
D.
Nairn and Hyman
Nairn and Hyman is a small township municipality in Northern Ontario, Canada, located within the Sudbury District.
-
E.
Fager
Fager is a surname most notably associated with American television producer and former CBS News chairman Jeff Fager.
- 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_69e0b4ce39108190a6e8e5df4f1c8dc5 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2fcc60881908ef3d8914d801ea1 |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.