Triple
T15582409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deborah Berke |
E374532
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Deborah Berke |
E374532
|
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: Deborah Berke | Statement: [Deborah Berke, name, Deborah Berke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deborah Berke Context triple: [Deborah Berke, name, Deborah Berke]
-
A.
Deborah Berke
chosen
Deborah Berke is an American architect and academic leader known for her modern, contextually sensitive designs and for serving as dean of the Yale School of Architecture.
-
B.
Elizabeth Diller
Elizabeth Diller is a prominent American architect and co-founder of the firm Diller Scofidio + Renfro, known for innovative cultural and public projects such as the High Line and the Broad museum.
-
C.
Jane Chermayeff
Jane Chermayeff is known as the spouse of renowned graphic designer Ivan Chermayeff.
-
D.
Catherine Chermayeff
Catherine Chermayeff is an American creative director, curator, and producer known for her work in photography, design, and cultural programming.
-
E.
Laurie Olin
Laurie Olin is a prominent American landscape architect and urban designer known for shaping major public spaces in cities across the United States.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e45ee3c8190a6aee06a5805ca39 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4f71e48190a15eb0a2138f083f |
completed | May 9, 2026, 3:01 p.m. |
Created at: April 10, 2026, 4:11 a.m.