Triple
T23586504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glycosmis |
E582358
|
entity |
| Predicate | hasFoliageCharacteristic |
P126358
|
FINISHED |
| Object | aromatic foliage |
—
|
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: aromatic foliage | Statement: [Glycosmis, hasFoliageCharacteristic, aromatic foliage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFoliageCharacteristic Context triple: [Glycosmis, hasFoliageCharacteristic, aromatic foliage]
-
A.
foliageCharacteristic
chosen
Indicates the specific traits or qualities of an entity’s foliage, such as its type, texture, color, or other distinguishing features.
-
B.
hasAttractiveFoliage
Indicates that an entity possesses foliage that is visually appealing or ornamental in appearance.
-
C.
hasVegetationRole
Indicates that an entity participates in or is assigned a specific functional role related to vegetation (such as growth, maintenance, or impact on plant life).
-
D.
typicalLeafCharacteristic
Indicates the usual or defining features of a leaf that characterize it under normal conditions.
-
E.
hasVegetationLayer
Indicates that an entity possesses a distinct layer or cover of vegetation as part of its structure or surface.
- 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_69e248f8d8248190acd5aee77f0d1709 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b03195748190b7e34f334902ac93 |
completed | April 29, 2026, 7:16 a.m. |
| PD | Predicate disambiguation | batch_69f118c96a0081908a8ac98ef7e7e60c |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:41 p.m.