Triple

T4721513
Position Surface form Disambiguated ID Type / Status
Subject Venice Marco Polo Airport E104776 entity
Predicate servesAsHubFor P423 FINISHED
Object Volotea
Volotea is a Spanish low-cost airline that primarily operates point-to-point flights connecting small and mid-sized European cities.
E464893 NE FINISHED

How this triple was built (4 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: [Venice Marco Polo Airport, servesAsHubFor, Volotea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Volotea
Context triple: [Venice Marco Polo Airport, servesAsHubFor, Volotea]
  • A. Kroitor
    Kroitor is a surname most notably associated with Roman Kroitor, a pioneering Canadian filmmaker and co-founder of IMAX.
  • B. Averostra
    Averostra is a major clade of theropod dinosaurs that includes many of the more derived, often carnivorous lineages such as ceratosaurs and tetanurans.
  • C. Grolleau
    Grolleau is a French red grape variety primarily used to produce light, fruity rosé and red wines, especially in the Anjou region.
  • D. Arkefly
    Arkefly was the former brand name of the Dutch leisure airline now known as TUI fly Netherlands, operating holiday flights to various destinations.
  • E. Orlybus
    Orlybus is a dedicated airport shuttle bus service connecting central Paris with Orly Airport.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Volotea
Triple: [Venice Marco Polo Airport, servesAsHubFor, Volotea]
Generated description
Volotea is a Spanish low-cost airline that primarily operates point-to-point flights connecting small and mid-sized European cities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Volotea
Target entity description: Volotea is a Spanish low-cost airline that primarily operates point-to-point flights connecting small and mid-sized European cities.
  • A. Kroitor
    Kroitor is a surname most notably associated with Roman Kroitor, a pioneering Canadian filmmaker and co-founder of IMAX.
  • B. Averostra
    Averostra is a major clade of theropod dinosaurs that includes many of the more derived, often carnivorous lineages such as ceratosaurs and tetanurans.
  • C. Grolleau
    Grolleau is a French red grape variety primarily used to produce light, fruity rosé and red wines, especially in the Anjou region.
  • D. Arkefly
    Arkefly was the former brand name of the Dutch leisure airline now known as TUI fly Netherlands, operating holiday flights to various destinations.
  • E. Orlybus
    Orlybus is a dedicated airport shuttle bus service connecting central Paris with Orly Airport.
  • F. None of above. chosen

Provenance (5 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_69bd43ec4a348190bc41afae43375e71 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd642a1a808190afeefc9d65e6c539 completed March 20, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69be1094fd9c81909e12723394f9ae0a completed March 21, 2026, 3:29 a.m.
NEDg Description generation batch_69be12b1c9088190bb6b307bfc46b75c completed March 21, 2026, 3:38 a.m.
NED2 Entity disambiguation (via description) batch_69be1318d494819084fac7c6d16db4e5 completed March 21, 2026, 3:40 a.m.
Created at: March 20, 2026, 1:18 p.m.