Triple
T26310367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mondrian dress |
E661803
|
entity |
| Predicate | associatedDesignerHouse |
P198819
|
FINISHED |
| Object | Yves Saint Laurent couture house |
—
|
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 couture house | Statement: [Mondrian dress, associatedDesignerHouse, Yves Saint Laurent couture house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedDesignerHouse Context triple: [Mondrian dress, associatedDesignerHouse, Yves Saint Laurent couture house]
-
A.
designerAlias
Indicates that one name or label is used as an alternative alias for a designer.
-
B.
designedBy
Indicates that one entity is the creator, planner, or architect responsible for the form or structure of another entity.
-
C.
designerCollaboratedWith
Indicates that a designer worked together with another party on a shared project or creative endeavor.
-
D.
designerBasedIn
Indicates that a designer carries out their professional activities or maintains their primary work location in a specified place.
-
E.
architectOfResidence
Indicates that one entity is the architect responsible for designing the residence 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_69ee812dacfc81908484aade9120fba9 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
| PDg | Predicate description generation | batch_69ff0d800ee88190835e233d9e846cdb |
completed | May 9, 2026, 10:33 a.m. |
Created at: April 26, 2026, 10:21 p.m.