Triple
T21862103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Four Seasons Hotel George V, Paris |
E539788
|
entity |
| Predicate | cuisineTypeAtLeGeorge |
P59511
|
FINISHED |
| Object | Mediterranean cuisine |
—
|
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: Mediterranean cuisine | Statement: [Four Seasons Hotel George V, Paris, cuisineTypeAtLeGeorge, Mediterranean cuisine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cuisineTypeAtLeGeorge Context triple: [Four Seasons Hotel George V, Paris, cuisineTypeAtLeGeorge, Mediterranean cuisine]
-
A.
chef-lieu
Indicates that one place serves as the administrative capital or main seat of government for a specified territorial division.
-
B.
cuisineType
Indicates the type or style of food associated with an entity, such as a restaurant or dish.
-
C.
haveCuisine
chosen
Indicates that an entity (such as a restaurant or place) offers, serves, or is associated with a particular type or style of cuisine.
-
D.
FrenchCouranteCharacteristic
Indicates that something possesses the stylistic or musical features typical of a French courante.
-
E.
cuisineSubtype
Indicates that one cuisine is a more specific subtype or variant within the broader category of another cuisine.
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0d63beb00819092b8ec3a8ef55a39 |
completed | April 28, 2026, 3:46 p.m. |
| PD | Predicate disambiguation | batch_69e6be9394f88190945ddd1dc004d29d |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:56 p.m.