Triple
T4247067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wizz Air |
E95554
|
entity |
| Predicate | hasHub |
P2413
|
FINISHED |
| Object | Sofia Airport |
E165787
|
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: Sofia Airport | Statement: [Wizz Air, hasHub, Sofia Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sofia Airport Context triple: [Wizz Air, hasHub, Sofia Airport]
-
A.
Sofia Airport
chosen
Sofia Airport is the main international airport serving Bulgaria’s capital city, Sofia, and one of the country’s busiest air transport hubs.
-
B.
Varna Airport
Varna Airport is an international airport serving the city of Varna and the surrounding Black Sea resort region in Bulgaria.
-
C.
Burgas Airport
Burgas Airport is an international airport on Bulgaria’s Black Sea coast that serves the city of Burgas and nearby seaside resorts.
-
D.
Niš Constantine the Great Airport
Niš Constantine the Great Airport is an international airport in Niš, Serbia, serving as a regional hub for low-cost and scheduled flights in the southern Balkans.
-
E.
Matei Airport
Matei Airport is a small regional airport serving the island of Taveuni in Fiji, providing domestic connections and access for tourists to the island’s resorts and natural attractions.
- 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_69b3453d91548190b4d4ef8fe52aa2ac |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e9b64ac81908dc44eaae6829b50 |
completed | March 12, 2026, 11:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a87c033881908e0cf9fdfecaf36a |
completed | March 14, 2026, 6:27 p.m. |
Created at: March 12, 2026, 11:05 p.m.