Triple
T17077368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sergio Costa |
E414384
|
entity |
| Predicate | brandScale |
P125780
|
FINISHED |
| Object | global coffeehouse chain |
—
|
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: global coffeehouse chain | Statement: [Sergio Costa, brandScale, global coffeehouse chain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandScale Context triple: [Sergio Costa, brandScale, global coffeehouse chain]
-
A.
brandLevel
Indicates the hierarchical rank or tier of a brand within a defined brand structure or classification system.
-
B.
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.
-
C.
favoriteBrand
Indicates that one entity is the preferred or most liked brand of another entity.
-
D.
brandNameType
Indicates the specific type or category associated with a brand name within a broader branding or naming system.
-
E.
brandRepresents
Indicates that a brand stands for, symbolizes, or conveys the identity, values, or characteristics of something.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc625c48190b679a521180e10ad |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
| PDg | Predicate description generation | batch_69e3753f93c88190808fec5692f66699 |
completed | April 18, 2026, 12:12 p.m. |
Created at: April 10, 2026, 5:34 a.m.