Triple
T36750863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erzincan tulum cheese |
E907907
|
entity |
| Predicate | storageEnvironment |
P853
|
FINISHED |
| Object | cool cellars |
—
|
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: cool cellars | Statement: [Erzincan tulum cheese, storageEnvironment, cool cellars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storageEnvironment Context triple: [Erzincan tulum cheese, storageEnvironment, cool cellars]
-
A.
storageProperty
Indicates a relationship where an entity has a specific storage-related characteristic, such as capacity, type, or configuration.
-
B.
storageDevice
Indicates a relationship where one entity functions as a device used to store data or digital information for another entity.
-
C.
storageFacility
Indicates a relationship where one entity serves as a place or facility used to store another entity or its items.
-
D.
storageOrgan
Indicates that one entity serves as a storage organ (a specialized structure for storing substances like nutrients or water) for another entity.
-
E.
environmentType
chosen
Indicates the kind or category of environment associated with an entity or situation.
- 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_69f76e76d10881909ec1679bc043108c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.