Triple
T36433737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophie Pera |
E897512
|
entity |
| Predicate | hasWorkedAsStylistFor |
P120057
|
FINISHED |
| Object | fashion editorials |
—
|
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: fashion editorials | Statement: [Sophie Pera, hasWorkedAsStylistFor, fashion editorials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkedAsStylistFor Context triple: [Sophie Pera, hasWorkedAsStylistFor, fashion editorials]
-
A.
stylist
chosen
Indicates that one entity serves as a stylist for another, providing professional advice or services related to appearance, fashion, or design.
-
B.
hasWorkedFor
Indicates that an entity has been employed by or has provided work or services to another entity.
-
C.
designerPreviouslyWorkedOn
Indicates that a designer has worked on the same or a related project in the past, prior to the current context or engagement.
-
D.
hasWorkedIn
Indicates that a person has been employed or has performed work within a particular organization, location, or domain for some period of time.
-
E.
hairCraftedBy
Indicates that a hairstyle or hair-related work was created or styled by a specific person or agent.
- 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_69f76e56636481908eda808ab0273401 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fec25f0fc48190b87ab1f9cd1eb0de |
completed | May 9, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69fec079a770819098df7cc3049df954 |
completed | May 9, 2026, 5:04 a.m. |
Created at: May 3, 2026, 4:10 p.m.