Triple
T23586534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glycosmis |
E582358
|
entity |
| Predicate | seedTrait |
P103508
|
FINISHED |
| Object | small seeds within fleshy fruits |
—
|
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: small seeds within fleshy fruits | Statement: [Glycosmis, seedTrait, small seeds within fleshy fruits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seedTrait Context triple: [Glycosmis, seedTrait, small seeds within fleshy fruits]
-
A.
agronomicTrait
Indicates a relationship where a trait is characterized specifically in terms of its relevance to agricultural growth, management, or productivity of plants or crops.
-
B.
seedProperty
Indicates that one entity serves as a seed or initial source from which the other entity’s properties, configuration, or content are derived or generated.
-
C.
breedingTrait
chosen
Indicates that an entity possesses a heritable characteristic that is relevant or targeted in a breeding process or program.
-
D.
seedType
Indicates the specific kind or category of seed associated with an entity.
-
E.
seedCoatCharacteristic
Indicates a relationship where a specific characteristic or property is attributed to the seed coat of an organism or specimen.
- 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.