Triple
T12284817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mai Tai |
E292801
|
entity |
| Predicate | servedOver |
P11944
|
FINISHED |
| Object | crushed 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: crushed ice | Statement: [Mai Tai, servedOver, crushed ice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedOver Context triple: [Mai Tai, servedOver, crushed ice]
-
A.
servedWith
chosen
Indicates that one item is customarily presented, provided, or consumed together with another as an accompaniment or side.
-
B.
served
Indicates that one entity provided a service, assistance, or role-based function to or for another entity.
-
C.
servedDuring
Indicates that one entity held a role, position, or performed a function within the time period defined by another entity.
-
D.
servedUntil
Indicates the ending time or date up to which an entity held a position, role, or service.
-
E.
servedHot
Indicates that something is provided or presented in a heated or warm state, suitable for immediate consumption.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d9261e1570819084bb4fdb44aa6aea |
completed | April 10, 2026, 4:32 p.m. |
| PD | Predicate disambiguation | batch_69d91c4d9a9c8190aeb7beaf9792d8f0 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.