Triple
T35428942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morbier cheese |
E1024000
|
entity |
| Predicate | traditionalAshSource |
P64939
|
FINISHED |
| Object | soot or vegetable ash |
—
|
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: soot or vegetable ash | Statement: [Morbier cheese, traditionalAshSource, soot or vegetable ash]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalAshSource Context triple: [Morbier cheese, traditionalAshSource, soot or vegetable ash]
-
A.
modernAshType
Indicates that an entity is classified as a modern type or form of ash.
-
B.
usesAshesFrom
chosen
Indicates that one entity makes use of ashes originating from another entity as a resource, material, or component in some process or context.
-
C.
smokestacks
Indicates the presence or involvement of smokestacks, typically as structures emitting smoke or exhaust as part of an industrial or energy-related process.
-
D.
traditionalOrigin
Indicates that something comes from, or is rooted in, a long-established cultural or customary source or practice.
-
E.
traditionalMaterial
Indicates that something is made from, incorporates, or is characterized by materials associated with long-established or customary practices.
- 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_69f76df743c48190aecb6dd79efb0d95 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 4:03 p.m.