Triple
T36286360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fukushima Airport |
E893093
|
entity |
| Predicate | hasFoodBeverageFacilities |
P70493
|
FINISHED |
| Object | restaurants |
—
|
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: restaurants | Statement: [Fukushima Airport, hasFoodBeverageFacilities, restaurants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFoodBeverageFacilities Context triple: [Fukushima Airport, hasFoodBeverageFacilities, restaurants]
-
A.
offersFoodAndBeverage
chosen
Indicates that an entity provides both food and drink to another entity or for general consumption.
-
B.
hasCateringServices
Indicates that an entity provides or offers catering services, such as preparing and supplying food and beverages for events or clients.
-
C.
hasFoodOrDrink
Indicates that an entity possesses, provides, or is associated with some type of food or drink.
-
D.
hasBeverageCategory
Indicates that an entity is associated with or classified under a particular beverage category.
-
E.
hasBeverageProduct
Indicates that one entity possesses, offers, or is associated with a particular beverage product.
- 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe86cad5108190b0164b8bc6fc23ea |
completed | May 9, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69fe83c0c9888190b6fc40c7f727b569 |
completed | May 9, 2026, 12:45 a.m. |
Created at: May 3, 2026, 4:09 p.m.