Triple
T26343849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Salamagne |
E662723
|
entity |
| Predicate | createdFragranceFor |
P174239
|
FINISHED |
| Object | Yves Saint Laurent |
—
|
NE NERFINISHED |
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: Yves Saint Laurent | Statement: [Marie Salamagne, createdFragranceFor, Yves Saint Laurent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdFragranceFor Context triple: [Marie Salamagne, createdFragranceFor, Yves Saint Laurent]
-
A.
launchedPerfume
Indicates that an entity has introduced or released a perfume product to the market.
-
B.
hasFragrance
Indicates that one entity possesses or emits a particular scent or aroma associated with another entity.
-
C.
hasFragranceForm
Indicates that an entity has a specific form or type of fragrance it is associated with or presented in.
-
D.
fragranceInspiration
Indicates that one entity serves as the creative or conceptual inspiration behind the fragrance of another entity.
-
E.
perfumeBottleDesign
Indicates a design relationship in which one entity is the specific aesthetic or structural design of a perfume bottle associated with another entity.
- F. None of above. chosen
Provenance (4 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_69ee81304194819092e20e0fae3aee07 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6bcc425588190afd0dceba43ed79f |
completed | May 3, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
| PDg | Predicate description generation | batch_69f6bbf5a8288190ae170bcbe8ab65cf |
completed | May 3, 2026, 3:07 a.m. |
Created at: April 26, 2026, 10:40 p.m.