Triple
T1543462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Business Select |
E32922
|
entity |
| Predicate | bookingChannel |
P6095
|
FINISHED |
| Object | Southwest Airlines 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: Southwest Airlines website | Statement: [Business Select, bookingChannel, Southwest Airlines website]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bookingChannel Context triple: [Business Select, bookingChannel, Southwest Airlines website]
-
A.
bookingOption
Indicates a selectable arrangement or choice available for making a booking, such as a specific time, package, or set of conditions under which a reservation can be made.
-
B.
hotelConnection
Indicates a relationship where one entity is linked or associated with a hotel, such as being located in, connected to, or serviced by that hotel.
-
C.
hotelBrand
Indicates that a hotel is affiliated with, operated by, or marketed under a specific hotel brand.
-
D.
reservationSystem
chosen
Indicates a system or process that manages the creation, modification, and tracking of reservations or bookings between parties.
-
E.
hotelOperator
Indicates that an entity operates, manages, or runs a hotel as its responsible service provider or business owner.
- 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_69a885ed29088190a3c2d5a3d100c16e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa95c1a2948190a2b98469afec1a7d |
completed | March 6, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_69a907b2453c8190a41f6b88c8217d1e |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.