Triple
T31601543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quillaja family |
E806360
|
entity |
| Predicate | memberProduces |
P490
|
FINISHED |
| Object | saponins |
—
|
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: saponins | Statement: [Quillaja family, memberProduces, saponins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memberProduces Context triple: [Quillaja family, memberProduces, saponins]
-
A.
producedMember
Indicates that one entity created, manufactured, or generated another entity as its product or output.
-
B.
producesFor
Indicates that one entity creates, manufactures, or generates something specifically intended for another entity’s use, benefit, or distribution.
-
C.
componentTypeProduced
Indicates that one entity produces or manufactures a specific type of component as an output of its activity or process.
-
D.
produces
chosen
Indicates that one entity creates, generates, or yields another entity as a result or output.
-
E.
includesProduce
Indicates that one entity contains or offers certain produce items as part of its contents, inventory, or offerings.
- 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_69f348d54ccc8190a03b5df9a2b40b25 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fbad1e94988190b86d447a68e65067 |
completed | May 6, 2026, 9:05 p.m. |
| PD | Predicate disambiguation | batch_69fba881b8e0819094790935152b99a1 |
completed | May 6, 2026, 8:45 p.m. |
Created at: April 30, 2026, 10:33 p.m.