Triple
T26037256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mario Prada |
E647585
|
entity |
| Predicate | hasBrandSpecialization |
P162908
|
FINISHED |
| Object | leather handbags |
—
|
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: leather handbags | Statement: [Mario Prada, hasBrandSpecialization, leather handbags]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBrandSpecialization Context triple: [Mario Prada, hasBrandSpecialization, leather handbags]
-
A.
hasBrandType
Indicates that an entity is associated with or categorized under a particular brand type or classification.
-
B.
hasBrandConcept
Indicates that an entity is associated with or embodies a particular brand concept or branding idea.
-
C.
hasBrandRole
Indicates that an entity holds a specific functional or organizational role in relation to a particular brand.
-
D.
isBrand
Indicates that one entity functions as the commercial brand or label associated with another entity.
-
E.
hasBrandName
Indicates that an entity is associated with or identified by a specific brand name.
- 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_69e77e8c88f08190858c4c81bd2e1b9a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f62e83045c8190a424a2e401a88e9e |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_69f62d886828819080ec2f742b9449e3 |
completed | May 2, 2026, 4:59 p.m. |
Created at: April 22, 2026, 9:08 a.m.