Triple
T3030685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marseille Provence Airport |
E82885
|
entity |
| Predicate | servesAsHubFor |
P423
|
FINISHED |
| Object | Ryanair |
E4144
|
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: Ryanair | Statement: [Marseille Provence Airport, servesAsHubFor, Ryanair]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ryanair Context triple: [Marseille Provence Airport, servesAsHubFor, Ryanair]
-
A.
Ryanair
chosen
Ryanair is a major Irish low-cost airline known for its extensive network of short-haul flights across Europe.
-
B.
Wizz Air
Wizz Air is a Hungarian ultra-low-cost airline known for operating an extensive network of budget flights across Europe and surrounding regions.
-
C.
Flynas
Flynas is a Saudi low-cost airline based in Riyadh that operates domestic and regional flights across the Middle East and beyond.
-
D.
Aer Lingus
Aer Lingus is the flag carrier airline of Ireland, operating international flights primarily between Ireland, Europe, and North America.
-
E.
Flybe
Flybe was a British regional airline that operated short-haul flights across the UK and Europe before ceasing operations.
- 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_69ad8b21a62881908ec5dd4fba4a187c |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9aecd384819085d15f701add7c44 |
completed | March 8, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1debd245c819081eb2dec470f9156 |
completed | March 11, 2026, 9:29 p.m. |
Created at: March 8, 2026, 3:01 p.m.