Triple
T12881733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiwi Starfruit Refresher |
E308111
|
entity |
| Predicate | intendedServingStyle |
P14779
|
FINISHED |
| Object | over ice |
—
|
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: over ice | Statement: [Kiwi Starfruit Refresher, intendedServingStyle, over ice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedServingStyle Context triple: [Kiwi Starfruit Refresher, intendedServingStyle, over ice]
-
A.
servingStyle
chosen
Indicates how something (typically food or drink) is presented or offered for consumption or use.
-
B.
diningStyle
Indicates the manner or format in which dining is conducted, such as casual, formal, buffet, or family-style.
-
C.
intendedToServe
Indicates that one entity was designed, planned, or purposed specifically to benefit, assist, or fulfill the needs of another entity.
-
D.
traditionallyServed
Indicates that one entity is customarily or conventionally presented, offered, or consumed together with another entity.
-
E.
isTypicallyServedFor
Indicates that one item is most commonly or customarily served as a meal or course for the other (e.g., a dish typically served for breakfast, lunch, or dinner).
- 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.