Triple
T28531232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milk |
E722046
|
entity |
| Predicate | typicalProteinContent |
P32526
|
FINISHED |
| Object | 3–3.5% for cow 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: 3–3.5% for cow milk | Statement: [Milk, typicalProteinContent, 3–3.5% for cow milk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalProteinContent Context triple: [Milk, typicalProteinContent, 3–3.5% for cow milk]
-
A.
proteinContent
chosen
Indicates the amount or proportion of protein present in a given entity or substance.
-
B.
typicalProtein
Indicates that one entity is a representative or characteristic example of a particular protein type or class.
-
C.
hasProtein
Indicates that one entity contains, includes, or is associated with a specific protein.
-
D.
isProtein
Indicates that the subject entity is classified as a protein.
-
E.
typicalProteinComponent
Indicates that one entity is a protein that commonly serves as a structural or functional component of another entity.
- 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_69f01a5d7ec88190ada2d5be7c06c35d |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a00b479c1588190af6e0698b7f8d7f7 |
completed | May 10, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_6a00b4158260819087d0cfad8b18cef4 |
completed | May 10, 2026, 4:36 p.m. |
Created at: April 28, 2026, 3:28 a.m.