Triple
T18783024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Collins |
E459305
|
entity |
| Predicate | servingMethod |
P14779
|
FINISHED |
| Object | on the rocks |
—
|
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: on the rocks | Statement: [Tom Collins, servingMethod, on the rocks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servingMethod Context triple: [Tom Collins, servingMethod, on the rocks]
-
A.
servingStyle
chosen
Indicates how something (typically food or drink) is presented or offered for consumption or use.
-
B.
servesMode
Indicates that one entity provides or operates in a particular manner, method, or mode in relation to another entity or context.
-
C.
servingPractice
Indicates a relationship where one entity engages in or performs a practice, routine, or exercise of serving (e.g., in a sport or service context).
-
D.
servesWith
Indicates that one entity is customarily presented, used, or consumed together with another as a complementary accompaniment.
-
E.
servesSide
Indicates that one entity is provided or presented as an accompanying side item to another primary 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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5977f34e48190a9932af330ea4f92 |
completed | April 20, 2026, 3:03 a.m. |
| PD | Predicate disambiguation | batch_69e48d16dd34819096e096d0c0e4c15c |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:52 a.m.