Triple
T38542020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Summer Shandy |
E924856
|
entity |
| Predicate | hasSubBrandExtensions |
P144439
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Summer Shandy, hasSubBrandExtensions, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubBrandExtensions Context triple: [Summer Shandy, hasSubBrandExtensions, yes]
-
A.
hasExtendedReleaseBrand
Indicates that a medication has a specific brand name corresponding to its extended-release formulation.
-
B.
hasNotableSubBrand
chosen
Indicates that an entity includes or owns a distinct, well-known sub-brand associated with it.
-
C.
hasBrandExtension
Indicates that a brand has been extended to additional products, services, or categories beyond its original offering.
-
D.
usedBySubBrand
Indicates that something (such as a resource, asset, or feature) is utilized or employed by a specific sub-brand within a larger brand structure.
-
E.
hasCoBrand
Indicates that two brands are jointly associated or partnered in offering a product, service, or marketing initiative.
- 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_69f76eadeac081909cdfdd0474cb6765 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a008c77d4dc8190b342d7407eaf48fa |
completed | May 10, 2026, 1:47 p.m. |
| PD | Predicate disambiguation | batch_6a008c18531c8190bbe883b73e6d023f |
completed | May 10, 2026, 1:46 p.m. |
Created at: May 3, 2026, 4:32 p.m.