Triple
T13657929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomme de Savoie |
E326909
|
entity |
| Predicate | typicalMilkTreatment |
P53129
|
FINISHED |
| Object | partially skimmed milk |
—
|
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: partially skimmed milk | Statement: [Tomme de Savoie, typicalMilkTreatment, partially skimmed milk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMilkTreatment Context triple: [Tomme de Savoie, typicalMilkTreatment, partially skimmed milk]
-
A.
milkTreatment
chosen
Indicates that an entity is subjected to a process or method of treating or processing milk.
-
B.
milkType
Indicates the specific kind or category of milk associated with an entity (e.g., whole, skim, plant-based).
-
C.
typicalMilkSource
Indicates that one entity is the usual or primary source from which the other entity obtains milk.
-
D.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
E.
milkComposition
Indicates the specific nutrients and components that make up a given sample of milk.
- 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_69d8076d8270819092afc2f0e9c359a8 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc61f0d808190b1cd2a6ba0d930eb |
completed | April 12, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69dbbe8a027081908d8f884b89707a5e |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:52 p.m.