Triple
T34173696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Australian Topaque |
E876608
|
entity |
| Predicate | consumptionMoment |
P104841
|
FINISHED |
| Object | after-dinner drink |
—
|
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: after-dinner drink | Statement: [Australian Topaque, consumptionMoment, after-dinner drink]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consumptionMoment Context triple: [Australian Topaque, consumptionMoment, after-dinner drink]
-
A.
commonlyConsumedAt
chosen
Indicates that one entity is typically eaten or drunk during, or in association with, a particular time, event, or context.
-
B.
consumptionWindow
Indicates the time period or conditions within which a resource, product, or content is intended or allowed to be used or consumed.
-
C.
consumptionState
Indicates the current status or condition of how something is being used up, consumed, or depleted.
-
D.
consumes
Indicates that one entity eats, drinks, or otherwise uses up another entity as a resource or nourishment.
-
E.
intendedConsumption
Indicates that one entity is meant or designed to be consumed or used up 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_69f349ad97ac8190bf1f17417c970e64 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f70fe7313c8190a4b8d08e659815c2 |
completed | May 3, 2026, 9:05 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:54 a.m.