Triple
T8536474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adriana Lima |
E202088
|
entity |
| Predicate | modeledFor |
P2006
|
FINISHED |
| Object | Valentino |
E57151
|
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: Valentino | Statement: [Adriana Lima, modeledFor, Valentino]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Valentino Context triple: [Adriana Lima, modeledFor, Valentino]
-
A.
Valentino
chosen
Valentino is a renowned Italian luxury fashion house celebrated for its elegant haute couture, ready-to-wear, and iconic red-carpet designs.
-
B.
Roberto Cavalli
Roberto Cavalli is an Italian fashion designer renowned for his glamorous, animal-print–driven aesthetic and luxury clothing and accessories brand.
-
C.
St. Laurent
St. Laurent is the surname of Louis St. Laurent, who served as the 12th prime minister of Canada in the mid-20th century.
-
D.
Edoardo Fendi
Edoardo Fendi was an Italian entrepreneur best known as the co-founder of the luxury fashion house Fendi, which began as a family-run leather and fur workshop in Rome.
-
E.
Versace
Versace is a renowned Italian luxury fashion house known for its bold, glamorous designs and iconic Medusa logo.
- 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6a3f024819095d560a205ff1c75 |
completed | March 31, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6d8332cc819083c86e0dc58bcc37 |
completed | April 2, 2026, 1:22 p.m. |
Created at: March 30, 2026, 6:18 p.m.