Triple

T5355939
Position Surface form Disambiguated ID Type / Status
Subject Air Transat E102691 entity
Predicate foundedBy P104 FINISHED
Object Lina De Cesare
Lina De Cesare is a Canadian business executive best known as a co-founder and longtime senior leader of the leisure airline and tour operator Air Transat.
 E518267 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: Lina De Cesare | Statement: [Air Transat, foundedBy, Lina De Cesare]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lina De Cesare
Context triple: [Air Transat, foundedBy, Lina De Cesare]
  • A. Elena Conti
    Elena Conti is an Italian structural biologist renowned for her pioneering work on RNA metabolism and macromolecular complexes, recognized by major scientific honors in molecular biology.
  • B. Lilia Vetti
    Lilia Vetti was the wife of famed French singer and actor Tino Rossi.
  • C. Tharita Cesaroni
    Tharita Cesaroni is an Italian film producer and cinematographer known for her work behind the camera and for being married to actor Dermot Mulroney.
  • D. Carla Leone
    Carla Leone was the wife of renowned Italian film director Sergio Leone.
  • E. Marcella De Marchis
    Marcella De Marchis was an Italian costume and production designer active in mid-20th-century cinema and theater.
  • 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: Lina De Cesare
Triple: [Air Transat, foundedBy, Lina De Cesare]
Generated description
Lina De Cesare is a Canadian business executive best known as a co-founder and longtime senior leader of the leisure airline and tour operator Air Transat.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lina De Cesare
Target entity description: Lina De Cesare is a Canadian business executive best known as a co-founder and longtime senior leader of the leisure airline and tour operator Air Transat.
  • A. Elena Conti
    Elena Conti is an Italian structural biologist renowned for her pioneering work on RNA metabolism and macromolecular complexes, recognized by major scientific honors in molecular biology.
  • B. Lilia Vetti
    Lilia Vetti was the wife of famed French singer and actor Tino Rossi.
  • C. Tharita Cesaroni
    Tharita Cesaroni is an Italian film producer and cinematographer known for her work behind the camera and for being married to actor Dermot Mulroney.
  • D. Carla Leone
    Carla Leone was the wife of renowned Italian film director Sergio Leone.
  • E. Marcella De Marchis
    Marcella De Marchis was an Italian costume and production designer active in mid-20th-century cinema and theater.
  • 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_69bd43d8f7248190b64c140734b5c9a8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd862f0ea48190bec78690ab3bee51 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3a9153d48190ae9263dc9073271c completed March 22, 2026, 12:40 a.m.
NEDg Description generation batch_69bf3b8c34d8819085bc9e0266c62a97 completed March 22, 2026, 12:45 a.m.
NED2 Entity disambiguation (via description) batch_69bf3bd788ec8190b17d9ddad3bb4a96 completed March 22, 2026, 12:46 a.m.
Created at: March 20, 2026, 2:01 p.m.