Triple
T17366306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luffa cylindrica |
E422196
|
entity |
| Predicate | fruitUseStage |
P51056
|
FINISHED |
| Object | used as sponge when fully mature and dried |
—
|
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: used as sponge when fully mature and dried | Statement: [Luffa cylindrica, fruitUseStage, used as sponge when fully mature and dried]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fruitUseStage Context triple: [Luffa cylindrica, fruitUseStage, used as sponge when fully mature and dried]
-
A.
culinaryUse
Indicates that one entity is used in the preparation, flavoring, or serving of food or drink for another entity.
-
B.
plantUse
chosen
Indicates that a plant is used for a particular purpose, function, or application.
-
C.
usedInPlant
Indicates that something is utilized or applied within a plant, such as in its processes, operations, or systems.
-
D.
fruitAdheresTo
Indicates that a fruit is physically attached or sticks to another surface or object.
-
E.
agricultureUse
Indicates that something is used for, involved in, or designated for agricultural activities or purposes.
- 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a50c9ec8190b518fdf80808af53 |
completed | April 19, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69e3b02662d08190a07d0fb5c04b6f33 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.