Triple
T20029974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fête du Cassoulet |
E495094
|
entity |
| Predicate | typeOfFoodCelebrated |
P122925
|
FINISHED |
| Object | slow-cooked bean stew |
—
|
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: slow-cooked bean stew | Statement: [Fête du Cassoulet, typeOfFoodCelebrated, slow-cooked bean stew]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFoodCelebrated Context triple: [Fête du Cassoulet, typeOfFoodCelebrated, slow-cooked bean stew]
-
A.
typeOfFoodFestival
chosen
Indicates the specific kind or category of food festival associated with an event or entity.
-
B.
feastType
Indicates the specific kind or category of feast associated with an event or occasion.
-
C.
feastRelatedTo
Indicates a relationship in which one entity is connected or relevant to a feast, such as by association, participation, context, or thematic linkage.
-
D.
holidayFood
Indicates that something is a type of food traditionally associated with or consumed during a holiday or festive occasion.
-
E.
isCelebratedWith
Indicates that an event, occasion, or person is marked or honored using a particular method, activity, or accompanying element (e.g., a party, ritual, or object).
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66291a00c8190b0b895909f32d623 |
completed | April 20, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69e54ce752748190a0a1ffddd0372271 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:36 p.m.