Triple
T11757700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruby (iMac G3 color) |
E279566
|
entity |
| Predicate | supportsBrandIdentityOf |
P48662
|
FINISHED |
| Object | colorful computers by Apple |
—
|
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: colorful computers by Apple | Statement: [Ruby (iMac G3 color), supportsBrandIdentityOf, colorful computers by Apple]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsBrandIdentityOf Context triple: [Ruby (iMac G3 color), supportsBrandIdentityOf, colorful computers by Apple]
-
A.
supportsBrand
Indicates that one entity endorses, promotes, or is compatible with a particular brand.
-
B.
hasBrandIdentityElement
chosen
Indicates that an entity includes or is associated with a specific component of its overall brand identity (such as a logo, color scheme, or tagline).
-
C.
supportsIdentity
Indicates that one entity upholds, validates, or reinforces the identity, self-concept, or role of another entity.
-
D.
sponsorBrandType
Indicates the type or category of brand that is acting as a sponsor in the relationship.
-
E.
maintainsBrandIdentityOf
Indicates that one entity preserves, protects, or upholds the established brand identity 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a50c8d708190ad79ecb57b715d04 |
completed | April 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69d88a829fe481909cc5431de7d6058e |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.