Triple
T14993093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cardiff Airport |
E373885
|
entity |
| Predicate | focusCityFor |
P164
|
FINISHED |
| Object | Wizz Air UK |
E95554
|
NE 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: Wizz Air UK | Statement: [Cardiff Airport, focusCityFor, Wizz Air UK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wizz Air UK Context triple: [Cardiff Airport, focusCityFor, Wizz Air UK]
-
A.
Wizz Air
chosen
Wizz Air is a Hungarian ultra-low-cost airline known for operating an extensive network of budget flights across Europe and surrounding regions.
-
B.
Ryanair
Ryanair is a major Irish low-cost airline known for its extensive network of short-haul flights across Europe.
-
C.
TUI Airways
TUI Airways is a British charter and scheduled airline that primarily serves leisure destinations across Europe and worldwide as part of the TUI Group.
-
D.
Flybe
Flybe was a British regional airline that operated short-haul flights across the UK and Europe before ceasing operations.
-
E.
Flynas
Flynas is a Saudi low-cost airline based in Riyadh that operates domestic and regional flights across the Middle East and beyond.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded716ebb481908224d2d4f7561b03 |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5aca8488190bf00bdbd7c4fb535 |
completed | May 9, 2026, 3:10 a.m. |
Created at: April 10, 2026, 2:53 a.m.