Triple
T17932091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lastminute.com |
E448356
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Booking.com |
—
|
NE NERFINISHED |
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: Booking.com | Statement: [Lastminute.com, competitor, Booking.com]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Booking.com Context triple: [Lastminute.com, competitor, Booking.com]
-
A.
Booking.com
chosen
Booking.com is a major global online travel agency that allows users to search for and book accommodations such as hotels, apartments, and vacation rentals.
-
B.
Agoda
Agoda is a global online travel agency known for offering hotel and accommodation bookings, flights, and travel services, particularly strong in the Asia-Pacific region.
-
C.
Klook
Klook is the nickname of Kenny Clarke, a pioneering American jazz drummer and key figure in the development of bebop.
-
D.
trivago
trivago is a global hotel and accommodation metasearch platform that compares prices from numerous booking sites to help users find and book lodging deals.
-
E.
Wotif Group
Wotif Group is an online travel company best known for its hotel and accommodation booking platforms, particularly in the Australian and Asia-Pacific markets.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a552bb848190871251474cc208d5 |
completed | April 19, 2026, 9:50 a.m. |
Created at: April 10, 2026, 10:20 a.m.