Triple
T21482145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adam Jones (Burnt) |
E530018
|
entity |
| Predicate | culinaryRecognitionGoal |
P86036
|
FINISHED |
| Object | three Michelin stars |
—
|
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: three Michelin stars | Statement: [Adam Jones (Burnt), culinaryRecognitionGoal, three Michelin stars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: culinaryRecognitionGoal Context triple: [Adam Jones (Burnt), culinaryRecognitionGoal, three Michelin stars]
-
A.
culinaryStatus
Indicates the current state or condition of something in relation to cooking or food preparation (e.g., raw, cooked, undercooked, burnt).
-
B.
knownForDish
Indicates that an entity is recognized or notable for preparing, serving, or being associated with a particular dish.
-
C.
hasCuisineRecognition
chosen
Indicates that an entity has received formal recognition, awards, or notable acknowledgment specifically for its cuisine.
-
D.
isCookedBy
Indicates that something has been prepared or made ready for eating through cooking by a particular agent.
-
E.
intendedMeal
Indicates that one entity is the meal that another entity plans or expects to eat.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea34c4388190adc78d209d2aafb8 |
completed | April 23, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69e631ec1d048190b6da97da8222e413 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:21 p.m.