Triple
T21517392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Peninsula Paris |
E530879
|
entity |
| Predicate | cuisineTypeAtLiLi |
P59511
|
FINISHED |
| Object | Cantonese 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: Cantonese cuisine | Statement: [The Peninsula Paris, cuisineTypeAtLiLi, Cantonese cuisine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cuisineTypeAtLiLi Context triple: [The Peninsula Paris, cuisineTypeAtLiLi, Cantonese cuisine]
-
A.
cuisineType
Indicates the type or style of food associated with an entity, such as a restaurant or dish.
-
B.
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.
-
C.
cuisineSubtype
Indicates that one cuisine is a more specific subtype or variant within the broader category of another cuisine.
-
D.
cuisine
Indicates the type or style of food traditionally associated with or served by an entity (such as a restaurant or region).
-
E.
cuisineFeature
Indicates a characteristic, quality, or notable aspect that describes or distinguishes a particular 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_69e0c45d95a081908e7962ad215da746 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee814278e08190a66d516bed0726b5 |
completed | April 26, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:25 p.m.