Triple
T2880204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starbucks Refreshers |
E56977
|
entity |
| Predicate | oftenCustomizedWith |
P33710
|
FINISHED |
| Object | lemonade |
—
|
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: lemonade | Statement: [Starbucks Refreshers, oftenCustomizedWith, lemonade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenCustomizedWith Context triple: [Starbucks Refreshers, oftenCustomizedWith, lemonade]
-
A.
customizableBy
chosen
Indicates that one entity can be modified, configured, or tailored in some way by another entity.
-
B.
custom
Indicates that something is specially created, configured, or tailored for a particular purpose, context, or user rather than being standard or generic.
-
C.
usedWith
Indicates that one entity is typically or appropriately employed together with another entity in a combined or complementary use.
-
D.
typicallySpared
Indicates that an entity is usually not affected by, excluded from, or left untouched by a particular action, process, or condition.
-
E.
adornedWith
Indicates that one entity is decorated, embellished, or ornamented by 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_69ab4a4ced288190ab6d3e062d10f7f6 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abe027beb88190ad191dba52b57454 |
completed | March 7, 2026, 8:21 a.m. |
| PD | Predicate disambiguation | batch_69abdd15cbf08190bf7fea5ea516848a |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:03 p.m.