Triple
T4460244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oscypek |
E98233
|
entity |
| Predicate | typicalMilkComposition |
P35422
|
FINISHED |
| Object | at least 60 percent sheep’s 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: at least 60 percent sheep’s milk | Statement: [Oscypek, typicalMilkComposition, at least 60 percent sheep’s milk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMilkComposition Context triple: [Oscypek, typicalMilkComposition, at least 60 percent sheep’s milk]
-
A.
milkComposition
chosen
Indicates the specific nutrients and components that make up a given sample of milk.
-
B.
typicalMilkSource
Indicates that one entity is the usual or primary source from which the other entity obtains milk.
-
C.
milkTreatment
Indicates that an entity is subjected to a process or method of treating or processing milk.
-
D.
typicalFatContent
Indicates the usual or characteristic amount of fat contained in something, such as a food or product.
-
E.
proteinContent
Indicates the amount or proportion of protein present in a given entity or substance.
- 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_69b3454a7c608190944f5455c8031d73 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35673337c8190b923159791ec27e3 |
completed | March 13, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69b34f65f6448190abfadb2ae5658798 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:33 p.m.