Triple
T28302851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ishigaki beef |
E713753
|
entity |
| Predicate | cookingRecommendation |
P14777
|
FINISHED |
| Object | medium-rare preparation |
—
|
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: medium-rare preparation | Statement: [Ishigaki beef, cookingRecommendation, medium-rare preparation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cookingRecommendation Context triple: [Ishigaki beef, cookingRecommendation, medium-rare preparation]
-
A.
cooksSimilarTo
Indicates that one entity prepares or cooks food in a way that is similar to how another entity does.
-
B.
recipe
Indicates that one entity is a set of instructions or method used to create, prepare, or produce another entity.
-
C.
intendedMeal
Indicates that one entity is the meal that another entity plans or expects to eat.
-
D.
genreOfRecipes
Indicates that one entity is a genre or category that characterizes the type or style of recipes associated with another entity.
-
E.
usesCookingMethod
chosen
Indicates that one entity prepares or processes another entity by applying a specific cooking technique or method.
- 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f644b3c6088190b3a20e8916fcddba |
completed | May 2, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 11:36 p.m.