Triple
T34224042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Smirnoff |
E877998
|
entity |
| Predicate | usesFiltration |
P62050
|
FINISHED |
| Object | charcoal filtration |
—
|
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: charcoal filtration | Statement: [Smirnoff, usesFiltration, charcoal filtration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesFiltration Context triple: [Smirnoff, usesFiltration, charcoal filtration]
-
A.
usesFilter
Indicates that one entity applies or employs a filter (such as a criterion, condition, or processing mechanism) to another entity or set of data.
-
B.
hasFiltration
chosen
Indicates that one entity is equipped with, performs, or is associated with a filtration process or system applied to another entity or substance.
-
C.
usesFilterSystem
Indicates that one entity employs or operates a filter system in relation to another entity or context.
-
D.
filtering
Indicates the process by which certain items, signals, or information are selectively included or excluded based on specified criteria or conditions.
-
E.
filter
Indicates that one entity selectively includes or excludes elements of another entity based on specified criteria or conditions.
- 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_69f349b16d0481908754e3069f05e0c1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f72ad38a208190b4bdc828297f86ad |
completed | May 3, 2026, 11 a.m. |
| PD | Predicate disambiguation | batch_69f72a0243988190a43b8ea22457cd30 |
completed | May 3, 2026, 10:57 a.m. |
Created at: May 1, 2026, 1:55 a.m.