Triple

T5989186
Position Surface form Disambiguated ID Type / Status
Subject Maurice Jarre E133300 entity
Predicate spouse P13 FINISHED
Object Dany Saval
Dany Saval is a French actress known for her film and television roles in the 1950s and 1960s.
E561018 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: Dany Saval | Statement: [Maurice Jarre, spouse, Dany Saval]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dany Saval
Context triple: [Maurice Jarre, spouse, Dany Saval]
  • A. Nicolas Tournier
    Nicolas Tournier was a French Baroque painter known for his dramatic use of light and shadow and religious scenes influenced by the style of Caravaggio.
  • B. Gaston Vidal
    Gaston Vidal was a French sports official and politician known for delivering the Olympic Oath at the 1924 Summer Olympics in Paris.
  • C. Bernard Arrazau
    Bernard Arrazau was one of the climbers credited with making the first recorded ascent of Aneto, the highest peak in the Pyrenees.
  • D. Dominique Tarlé
    Dominique Tarlé is a French photographer best known for his intimate, behind-the-scenes images of rock musicians, particularly The Rolling Stones in the early 1970s.
  • E. Juan Barrundia
    Juan Barrundia was a 19th-century Central American liberal politician who served as head of state of Guatemala during the early years of the Federal Republic of Central America.
  • 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: Dany Saval
Triple: [Maurice Jarre, spouse, Dany Saval]
Generated description
Dany Saval is a French actress known for her film and television roles in the 1950s and 1960s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dany Saval
Target entity description: Dany Saval is a French actress known for her film and television roles in the 1950s and 1960s.
  • A. Nicolas Tournier
    Nicolas Tournier was a French Baroque painter known for his dramatic use of light and shadow and religious scenes influenced by the style of Caravaggio.
  • B. Gaston Vidal
    Gaston Vidal was a French sports official and politician known for delivering the Olympic Oath at the 1924 Summer Olympics in Paris.
  • C. Bernard Arrazau
    Bernard Arrazau was one of the climbers credited with making the first recorded ascent of Aneto, the highest peak in the Pyrenees.
  • D. Dominique Tarlé
    Dominique Tarlé is a French photographer best known for his intimate, behind-the-scenes images of rock musicians, particularly The Rolling Stones in the early 1970s.
  • E. Juan Barrundia
    Juan Barrundia was a 19th-century Central American liberal politician who served as head of state of Guatemala during the early years of the Federal Republic of Central America.
  • 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_69c0087010d081908bb8142342d63330 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04dc76fd481908cc3f327e532a1a6 completed March 22, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c10854969c8190b9be249f26ad2f47 completed March 23, 2026, 9:31 a.m.
NEDg Description generation batch_69c109bf2fb4819091915b2e10b629b8 completed March 23, 2026, 9:37 a.m.
NED2 Entity disambiguation (via description) batch_69c10a5e061c81909e8085f3210452dc completed March 23, 2026, 9:39 a.m.
Created at: March 22, 2026, 4:04 p.m.