Triple
T456726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khachapuri |
E7248
|
entity |
| Predicate | hasPreparationStep |
P9959
|
FINISHED |
| Object | kneading dough |
—
|
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: kneading dough | Statement: [Khachapuri, hasPreparationStep, kneading dough]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreparationStep Context triple: [Khachapuri, hasPreparationStep, kneading dough]
-
A.
hasStep
chosen
Indicates that one entity includes, is composed of, or is associated with a specific step or stage in a process involving another entity.
-
B.
preparesFor
Indicates that one entity is used, designed, or undertaken in order to get another entity ready for a future event, state, or activity.
-
C.
isCookedBy
Indicates that something has been prepared or made ready for eating through cooking by a particular agent.
-
D.
requiresCookingTemperature
Indicates that performing the action or preparing the item necessitates reaching or maintaining a specific cooking temperature.
-
E.
hasMainIngredient
Indicates that one entity is the primary or most significant ingredient used to make 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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efa1616481909399f92551a0c9e3 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede614b88190be07425f5535f56d |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.