Triple
T38173372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bahian cuisine |
E1000137
|
entity |
| Predicate | streetFoodSpecialty |
P8359
|
FINISHED |
| Object | acarajé |
—
|
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: acarajé | Statement: [Bahian cuisine, streetFoodSpecialty, acarajé]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: streetFoodSpecialty Context triple: [Bahian cuisine, streetFoodSpecialty, acarajé]
-
A.
hasStreetFood
chosen
Indicates that one entity offers, features, or is associated with street food in relation to another entity.
-
B.
foodCustom
Indicates a culturally specific practice, rule, or tradition related to the preparation, serving, or consumption of food.
-
C.
typeOfFoodFestival
Indicates the specific kind or category of food festival associated with an event or entity.
-
D.
foodService
Indicates that one entity provides, manages, or is responsible for supplying food or meal-related services to another entity.
-
E.
storesFood
Indicates that one entity keeps or holds food items for future use or consumption.
- 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_69f76daaace48190a38cee37f8ce343f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:29 p.m.