Triple
T10004442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Behati Prinsloo |
E198206
|
entity |
| Predicate | hasWalkedRunwayFor |
P91523
|
FINISHED |
| Object | Prada |
E31748
|
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: Prada | Statement: [Behati Prinsloo, hasWalkedRunwayFor, Prada]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prada Context triple: [Behati Prinsloo, hasWalkedRunwayFor, Prada]
-
A.
Prada
chosen
Prada is a renowned Italian luxury fashion house known for its high-end clothing, leather goods, and accessories.
-
B.
Gucci
Gucci is a renowned Italian luxury fashion house known for its high-end clothing, accessories, and iconic branding.
-
C.
Fendi
Fendi is a renowned Italian luxury fashion house known for its high-end clothing, leather goods, and iconic handbags.
-
D.
Louis Vuitton
Louis Vuitton is a French luxury fashion house and brand renowned worldwide for its high-end leather goods, ready-to-wear, accessories, and iconic monogram designs.
-
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_69ca830fcca48190bbbd9b20c233835f |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd141ec08190b857fe7e15a8df93 |
completed | April 2, 2026, 1:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2cb8b92b0819081e5ac52e2f4f27e |
completed | April 5, 2026, 8:52 p.m. |
Created at: March 30, 2026, 8:51 p.m.