Triple
T1276979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keitt mango |
E27236
|
entity |
| Predicate | storageCharacteristic |
P25913
|
FINISHED |
| Object | stores well under refrigeration |
—
|
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: stores well under refrigeration | Statement: [Keitt mango, storageCharacteristic, stores well under refrigeration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storageCharacteristic Context triple: [Keitt mango, storageCharacteristic, stores well under refrigeration]
-
A.
equipmentCharacteristic
Indicates that a specific characteristic, property, or attribute is associated with a piece of equipment.
-
B.
storageQuality
chosen
Indicates the degree or standard of how well something is stored, such as its preservation, safety, or suitability for use.
-
C.
transportCharacteristic
Indicates a relationship where a specific characteristic, property, or feature is attributed to a mode or instance of transport.
-
D.
storageOption
Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
-
E.
pricingCharacteristic
Indicates how the price of something is determined, structured, or behaves (e.g., fixed, variable, discounted, tiered).
- 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_69a496d3710c8190955dee8bc0dacb50 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c31602b8819087a57e8d390cae7a |
completed | March 1, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69a4bee0be808190a8ccac6a41851fdd |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:50 p.m.