Triple
T8751757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pecorino Toscano |
E207974
|
entity |
| Predicate | requiresMilkFrom |
P55254
|
FINISHED |
| Object | sheep raised in designated production area |
—
|
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: sheep raised in designated production area | Statement: [Pecorino Toscano, requiresMilkFrom, sheep raised in designated production area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresMilkFrom Context triple: [Pecorino Toscano, requiresMilkFrom, sheep raised in designated production area]
-
A.
milkType
Indicates the specific kind or category of milk associated with an entity (e.g., whole, skim, plant-based).
-
B.
feedingType
Indicates the manner or method by which one entity provides nourishment or food to another.
-
C.
milkTreatment
Indicates that an entity is subjected to a process or method of treating or processing milk.
-
D.
milkComposition
Indicates the specific nutrients and components that make up a given sample of milk.
-
E.
typicalMilkSource
chosen
Indicates that one entity is the usual or primary source from which the other entity obtains 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_69ca835cd6b08190bd7c63db92f53c86 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5da774f4819099e5bfd12973d946 |
completed | March 31, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69cc5c160dac8190b4aeb4bf0529de52 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:39 p.m.