Triple
T30312757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | chicken tempura (toriten) |
E770969
|
entity |
| Predicate | batterIngredients |
P12771
|
FINISHED |
| Object | wheat flour |
—
|
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: wheat flour | Statement: [chicken tempura (toriten), batterIngredients, wheat flour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: batterIngredients Context triple: [chicken tempura (toriten), batterIngredients, wheat flour]
-
A.
batter
Indicates that one entity physically strikes or beats another entity, typically with repeated or forceful blows.
-
B.
typicalIngredientRatio
Indicates the usual proportional relationship between different ingredients used together in a preparation or mixture.
-
C.
ingredientType
Indicates that one entity is classified as a specific type or category of ingredient in relation to another.
-
D.
usesIngredient
chosen
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
-
E.
BakerYield
Indicates the amount or output produced by a baker, typically in terms of quantity or volume of baked goods resulting from a given process or batch.
- 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_69f22488f224819081b0f3ec41ab975c |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6816ceb688190b2e5f01205f3c550 |
completed | May 2, 2026, 10:57 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 7:50 p.m.