Triple
T18749234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flying Returns |
E458481
|
entity |
| Predicate | supportsBookingChannel |
P31089
|
FINISHED |
| Object | Air India website |
—
|
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: Air India website | Statement: [Flying Returns, supportsBookingChannel, Air India website]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsBookingChannel Context triple: [Flying Returns, supportsBookingChannel, Air India website]
-
A.
hasBookingChannel
chosen
Indicates that an entity is associated with or obtained through a particular method or platform used to make a booking.
-
B.
supportsBuyingChannel
Indicates that one entity enables, allows, or is compatible with a particular buying or purchasing channel used by another entity.
-
C.
supportsChannels
Indicates that one entity is capable of handling, providing, or being compatible with one or more specified channels for communication, distribution, or operation.
-
D.
bookingModel
Indicates a relationship where an entity uses or is associated with a specific model or schema that defines how bookings are structured, processed, or represented.
-
E.
alsoBookableAs
Indicates that one entity can be reserved or booked in an alternative way or under an alternative option represented by another entity.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579eb7350819099d7291207781116 |
completed | April 20, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e48d0b7b708190877951b6e6cdcbc4 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:51 a.m.