Triple
T35006470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Makó onion |
E1009821
|
entity |
| Predicate | roleInCuisine |
P129066
|
FINISHED |
| Object | base ingredient for many Hungarian dishes |
—
|
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: base ingredient for many Hungarian dishes | Statement: [Makó onion, roleInCuisine, base ingredient for many Hungarian dishes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInCuisine Context triple: [Makó onion, roleInCuisine, base ingredient for many Hungarian dishes]
-
A.
roleInFood
chosen
Indicates the functional role or purpose that an entity has within a food item, product, or context (e.g., ingredient, flavoring, preservative).
-
B.
worksInKitchenAt
Indicates that an entity performs work or duties in the kitchen area of a specified location or organization.
-
C.
roleInCoco
Indicates that an entity serves a specific role or function within the context of the COCO dataset or framework.
-
D.
culinaryForm
Indicates the specific style, preparation method, or culinary format in which a food item or dish is presented or made.
-
E.
roleInVega
Indicates that an entity holds a specific role or function within the Vega context (such as the Vega project, system, or framework).
- 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_69f76dcb716881909f75e4fd60ab2284 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a011c64ff18819099195701bbecbb20 |
completed | May 11, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_6a011b7f7a508190b2ebb518fb7a2fe9 |
completed | May 10, 2026, 11:57 p.m. |
Created at: May 3, 2026, 4:01 p.m.