Triple
T29007243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French press |
E736468
|
entity |
| Predicate | filterRetention |
P36260
|
FINISHED |
| Object | low fines retention |
—
|
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: low fines retention | Statement: [French press, filterRetention, low fines retention]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filterRetention Context triple: [French press, filterRetention, low fines retention]
-
A.
leafRetention
Indicates whether an entity retains its leaves (e.g., remains evergreen) or sheds them seasonally.
-
B.
filter
Indicates that one entity selectively includes or excludes elements of another entity based on specified criteria or conditions.
-
C.
filtering
Indicates the process by which certain items, signals, or information are selectively included or excluded based on specified criteria or conditions.
-
D.
filterSystem
Indicates that one entity functions to remove or separate unwanted components, substances, or signals from another entity or system.
-
E.
filterType
chosen
Indicates the specific category or method of filtering that is applied to a set of items or data.
- 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_69f077eb81e88190ad9ff62cbb9f555e |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f65fd9cb788190beb90acc39f381b1 |
completed | May 2, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 9:39 a.m.