Triple
T20511084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cavendish bananas |
E503561
|
entity |
| Predicate | harvestedWhen |
P23127
|
FINISHED |
| Object | green and unripe |
—
|
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: green and unripe | Statement: [Cavendish bananas, harvestedWhen, green and unripe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: harvestedWhen Context triple: [Cavendish bananas, harvestedWhen, green and unripe]
-
A.
isHarvestedBy
Indicates that something (typically a resource, crop, or material) is collected or gathered through the actions of a particular agent or method.
-
B.
isTypicallyHarvested
Indicates that an entity is commonly gathered or collected, usually at a particular time or stage, for use or consumption.
-
C.
harvestCondition
chosen
Indicates the specific circumstances or criteria under which a harvest may or should be carried out.
-
D.
harvestSize
Indicates the quantity or scale of yield obtained from a harvesting activity.
-
E.
harvestPart
Indicates that one entity is a component or portion that is removed or collected from another entity during a harvesting process.
- 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_69e0b4b2aa788190ae9eb37c1d73b1f1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69dcb8f5c8190b0d4c09f3669a8ec |
completed | April 20, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69e59fdb7ad88190924176c32a195db3 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:36 a.m.