Triple
T29298724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Indian cuisine |
E742901
|
entity |
| Predicate | usesFermentedFoods |
P149950
|
FINISHED |
| Object | idli batter |
—
|
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: idli batter | Statement: [South Indian cuisine, usesFermentedFoods, idli batter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesFermentedFoods Context triple: [South Indian cuisine, usesFermentedFoods, idli batter]
-
A.
usesFermentedProduct
chosen
Indicates that one entity employs or incorporates a fermented product in relation to another entity or activity.
-
B.
fermentedFood
Indicates that one entity is a food item that has been produced or altered through a fermentation process involving microorganisms.
-
C.
isFermentedAs
Indicates that one substance undergoes a fermentation process to become another specified product.
-
D.
mustBeFermentedBy
Indicates that one entity is required to undergo a fermentation process carried out by another specified entity.
-
E.
fermentationAgent
Indicates that one entity serves as the agent or catalyst that carries out the fermentation process on 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_69f0912323c48190b9a24ef8cf359225 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f67f7efc3c8190986d2d95b7a23729 |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 28, 2026, 1:08 p.m.