Triple
T1528862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Helena Christensen |
E32395
|
entity |
| Predicate | workedFor |
P1910
|
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: [Helena Christensen, workedFor, Prada]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prada Context triple: [Helena Christensen, workedFor, Prada]
-
A.
Prada
chosen
Prada is a renowned Italian luxury fashion house known for its high-end clothing, leather goods, and accessories.
-
B.
Fendi
Fendi is a renowned Italian luxury fashion house known for its high-end clothing, leather goods, and iconic handbags.
-
C.
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.
-
D.
Versace
Versace is a renowned Italian luxury fashion house known for its bold, glamorous designs and iconic Medusa logo.
-
E.
Balenciaga
Balenciaga is a luxury French fashion house renowned for its avant-garde, architectural designs and influential role in high fashion.
- 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_69a885ea86308190998f6bc14bb91f8e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb1dfd1a48190804ca5f0fb6f5985 |
completed | March 7, 2026, 5:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad309188508190840af75bfa357bfb |
completed | March 8, 2026, 8:17 a.m. |
Created at: March 4, 2026, 7:26 p.m.