Triple
T14048668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pinangat |
E338025
|
entity |
| Predicate | usesPlantPart |
P51054
|
FINISHED |
| Object | taro leaves |
—
|
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: taro leaves | Statement: [Pinangat, usesPlantPart, taro leaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesPlantPart Context triple: [Pinangat, usesPlantPart, taro leaves]
-
A.
hasPlantPart
chosen
Indicates that one entity includes, contains, or is composed of a specific plant part of another entity.
-
B.
affectsPlantPart
Indicates that one entity produces an influence, change, or impact on a specific part of a plant.
-
C.
involvesPlant
Indicates that the relationship or action includes or pertains to a plant as a participating entity.
-
D.
isPlantOf
Indicates that one entity is a plant that belongs to, is associated with, or is characteristic of another entity (such as a region, habitat, or owner).
-
E.
containsPlantsWith
Indicates that one entity includes or holds within it one or more plant entities.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de3c88b5e48190b0f0149102c08992 |
completed | April 14, 2026, 1:09 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:20 p.m.