Triple
T5179873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nantes Atlantique Airport |
E116892
|
entity |
| Predicate | hasFocusCityFor |
P1295
|
FINISHED |
| Object | Volotea |
E464893
|
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: Volotea | Statement: [Nantes Atlantique Airport, hasFocusCityFor, Volotea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Volotea Context triple: [Nantes Atlantique Airport, hasFocusCityFor, Volotea]
-
A.
Volotea
chosen
Volotea is a Spanish low-cost airline that primarily operates point-to-point flights connecting small and mid-sized European cities.
-
B.
Volans
Volans is a small southern sky constellation representing a flying fish, located near the Large Magellanic Cloud.
-
C.
Kroitor
Kroitor is a surname most notably associated with Roman Kroitor, a pioneering Canadian filmmaker and co-founder of IMAX.
-
D.
Averostra
Averostra is a major clade of theropod dinosaurs that includes many of the more derived, often carnivorous lineages such as ceratosaurs and tetanurans.
-
E.
Grolleau
Grolleau is a French red grape variety primarily used to produce light, fruity rosé and red wines, especially in the Anjou region.
- 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_69bd446140f08190becb93c61158f27f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd79978a208190b2e5909795108327 |
completed | March 20, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed9553bc0819082a37a83a3edf7e8 |
completed | March 21, 2026, 5:45 p.m. |
Created at: March 20, 2026, 1:45 p.m.