Triple
T8987500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Hurley |
E214704
|
entity |
| Predicate | fashionIconFor |
P29718
|
FINISHED |
| Object | Versace safety-pin dress look |
—
|
LITERAL 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: Versace safety-pin dress look | Statement: [Elizabeth Hurley, fashionIconFor, Versace safety-pin dress look]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fashionIconFor Context triple: [Elizabeth Hurley, fashionIconFor, Versace safety-pin dress look]
-
A.
fashionCharacteristic
Indicates a relationship where one entity possesses or exhibits a particular style, trend, or fashion-related attribute in relation to another.
-
B.
fashionLabel
Indicates that an entity is a fashion brand or label associated with the design, production, or marketing of clothing or accessories.
-
C.
fashionStyle
Indicates the characteristic way in which an entity dresses or presents themselves in terms of clothing and appearance.
-
D.
fashionReputation
chosen
Indicates the perceived status or esteem an entity holds within the context of fashion, based on how its style, taste, or influence is judged by others.
-
E.
iconOf
Indicates that one entity serves as a symbolic or representative image or emblem of another entity.
- F. None of above.
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_69ca839f76bc8190a4b7123cdd682199 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67ef19108190ac518c4f744b6d60 |
completed | April 1, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69cc5edba0f88190b97401636a076d7a |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:04 p.m.