Triple
T23265251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japan Airlines First Class Lounge |
E588128
|
entity |
| Predicate | targetPassengerClass |
P127050
|
FINISHED |
| Object | First Class |
—
|
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: First Class | Statement: [Japan Airlines First Class Lounge, targetPassengerClass, First Class]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetPassengerClass Context triple: [Japan Airlines First Class Lounge, targetPassengerClass, First Class]
-
A.
seatClass
Indicates the travel or seating category assigned to a passenger or seat (e.g., economy, business, first class).
-
B.
appliesToPassengerType
Indicates that a rule, condition, or attribute is relevant or restricted to a specific type or category of passenger.
-
C.
airlineClass
Indicates the specific travel class or service level assigned to a passenger or ticket on an airline flight.
-
D.
servesCabinClass
chosen
Indicates that a service provider (such as an airline or flight) offers or is available to a specified cabin class (e.g., economy, business, first).
-
E.
cabinClassAbove
Indicates that one cabin class is ranked higher or more premium than another in a class hierarchy.
- 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f194cc3b908190aaefd036aa2b52b5 |
completed | April 29, 2026, 5:19 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:34 p.m.