Triple
T13903158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Longjing tea |
E334278
|
entity |
| Predicate | recommendedStorage |
P8611
|
FINISHED |
| Object | airtight container |
—
|
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: airtight container | Statement: [Longjing tea, recommendedStorage, airtight container]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recommendedStorage Context triple: [Longjing tea, recommendedStorage, airtight container]
-
A.
recommendedLocation
Indicates that one entity suggests or endorses another entity as a suitable or preferred place for a particular purpose or activity.
-
B.
storageOption
chosen
Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
-
C.
recommendedMode
Indicates that one entity is suggested or advised as the preferred mode, method, or way of doing or experiencing something in relation to another entity.
-
D.
commendedFor
Indicates that one entity has expressed praise or approval toward another entity specifically because of a particular action, quality, or achievement.
-
E.
storageOrgan
Indicates that one entity serves as a storage organ (a specialized structure for storing substances like nutrients or water) for 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de25db1e308190aaed6a21e443cc44 |
completed | April 14, 2026, 11:32 a.m. |
| PD | Predicate disambiguation | batch_69dd464b1ab48190ae50bfc902bf6ef7 |
completed | April 13, 2026, 7:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.