Triple
T31601560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quillaja family |
E806360
|
entity |
| Predicate | containsBioactiveCompounds |
P73953
|
FINISHED |
| Object | triterpenoid 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: triterpenoid saponins | Statement: [Quillaja family, containsBioactiveCompounds, triterpenoid saponins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsBioactiveCompounds Context triple: [Quillaja family, containsBioactiveCompounds, triterpenoid saponins]
-
A.
hasBiologicalComponents
chosen
Indicates that an entity is composed of, contains, or is associated with one or more biological parts or substances.
-
B.
hasBioavailability
Indicates that a substance has a specified degree or measure of bioavailability, i.e., the proportion that enters circulation and can have an active effect.
-
C.
containsAlkaloids
Indicates that a substance, organism, or material has alkaloid compounds present within it.
-
D.
hasActiveMetabolite
Indicates that a substance produces one or more metabolites that remain pharmacologically active in the body.
-
E.
containsAllergenicCompound
Indicates that the subject entity includes one or more compounds known to cause allergic reactions.
- 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_69ff8cecbf048190860b9f72b8753f5c |
completed | May 9, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69ff8c4c39dc8190b5bf35adc1bae7c6 |
completed | May 9, 2026, 7:34 p.m. |
Created at: April 30, 2026, 10:33 p.m.