Triple
T4073384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Problem Solvers (historical) |
E86700
|
entity |
| Predicate | brandElementOf |
P48662
|
FINISHED |
| Object | UPS marketing strategy |
—
|
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: UPS marketing strategy | Statement: [United Problem Solvers (historical), brandElementOf, UPS marketing strategy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandElementOf Context triple: [United Problem Solvers (historical), brandElementOf, UPS marketing strategy]
-
A.
parentBrand
Indicates that one brand is the overarching or owning brand from which another brand is derived or subordinated.
-
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.
brand
Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
-
D.
usedBrand
Indicates that an entity has utilized, applied, or operated a particular brand in some context.
-
E.
hasBrandName
Indicates that an entity is associated with or identified by a specific brand name.
- 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_69aed93ebe448190a1f1686e28740ac9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc22be988190a2b6575d4f5e0f7b |
completed | March 9, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69aef9061d2481908307cafc9e9b32c0 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:39 p.m.