Triple
T15284639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ohr-O’Keefe Museum of Art |
E365362
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Frank Gehry |
E6555
|
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: Frank Gehry | Statement: [Ohr-O’Keefe Museum of Art, architect, Frank Gehry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Gehry Context triple: [Ohr-O’Keefe Museum of Art, architect, Frank Gehry]
-
A.
Frank Gehry
chosen
Frank Gehry is a renowned Canadian-American architect celebrated for his innovative, sculptural, and deconstructivist building designs worldwide.
-
B.
Thom Mayne
Thom Mayne is an American architect and founder of the firm Morphosis, known for his bold, unconventional designs and influential role in contemporary architecture.
-
C.
Richard Meier
Richard Meier is an American architect renowned for his modernist, white geometric designs and major cultural projects such as the Getty Center in Los Angeles.
-
D.
Román Viñoly
Román Viñoly is a member of the Viñoly family, known primarily as the son of acclaimed Uruguayan architect Rafael Viñoly.
-
E.
Jean Nouvel
Jean Nouvel is a renowned French architect celebrated for his innovative, context-sensitive designs on landmark projects around the world.
- 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_69d85a103d9081908c1ea6c4c73ac8e3 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00e53c9588190a6cb61ac8805c706 |
completed | April 15, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feef798a588190981c77e6f4c6be78 |
completed | May 9, 2026, 8:25 a.m. |
Created at: April 10, 2026, 3:15 a.m.