Triple
T22662017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuber |
E559687
|
entity |
| Predicate | odorRole |
P68445
|
FINISHED |
| Object | attracts animals for spore dispersal |
—
|
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: attracts animals for spore dispersal | Statement: [Tuber, odorRole, attracts animals for spore dispersal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: odorRole Context triple: [Tuber, odorRole, attracts animals for spore dispersal]
-
A.
odor
Indicates that one entity emits, possesses, or is characterized by a particular smell detectable by another entity.
-
B.
გვარი
Indicates a relationship where one entity is the family name or surname of another entity.
-
C.
odorResponse
Indicates a relationship where an entity exhibits a measurable reaction or change in behavior, physiology, or activity in response to an odor stimulus.
-
D.
biologicalRole
chosen
Indicates the functional role or purpose that one biological entity has in relation to another or within a biological process.
-
E.
sonRole
Indicates that one entity holds the role or relationship of a son with respect to another entity.
- 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765fe7d081908087778c54c1e612 |
completed | April 29, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69ee62a6245881909506ff502da14137 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:08 p.m.