Triple
T11885609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donna |
E282771
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Donna Karan |
E761432
|
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: Donna Karan | Statement: [Donna, hasNotableBearer, Donna Karan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donna Karan Context triple: [Donna, hasNotableBearer, Donna Karan]
-
A.
Donna Karan
chosen
Donna Karan is an influential American fashion designer best known for founding the DKNY label and redefining modern women’s workwear with her sleek, versatile designs.
-
B.
Diane von Fürstenberg
Diane von Fürstenberg is a Belgian-born fashion designer best known for creating the iconic wrap dress and founding her eponymous global luxury brand.
-
C.
Carolina Herrera
Carolina Herrera is a Venezuelan-American fashion designer renowned for her elegant, sophisticated clothing and fragrance lines favored by celebrities and socialites.
-
D.
Cynthia Rowley
Cynthia Rowley is an American fashion designer known for her playful, colorful, and adventurous ready-to-wear and accessories collections.
-
E.
Nicole Miller
Nicole Miller is an American fashion designer renowned for her modern, feminine womenswear and bold use of color and print.
- 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_69d6ab2a90b08190a4e818821cc93e6d |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d3a13370819086386fecb99e4f0b |
completed | April 10, 2026, 10:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281f488a8819082f40dfdd12f29a2 |
completed | April 29, 2026, 10:11 p.m. |
Created at: April 8, 2026, 9:44 p.m.