Triple

T20015046
Position Surface form Disambiguated ID Type / Status
Subject Vivo per lei E494694 entity
Predicate performedAsDuetWith P9649 FINISHED
Object Hélène Ségara NE NERFINISHED

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: Hélène Ségara | Statement: [Vivo per lei, performedAsDuetWith, Hélène Ségara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hélène Ségara
Context triple: [Vivo per lei, performedAsDuetWith, Hélène Ségara]
  • A. Hélène Ségara chosen
    Hélène Ségara is a French pop singer and musical theatre performer best known internationally for playing Esmeralda in the hit stage musical Notre-Dame de Paris.
  • B. Mireille Mathieu
    Mireille Mathieu is a French chanteuse renowned for her powerful voice, classic chanson repertoire, and international success since the 1960s.
  • C. Sylvie Vartan
    Sylvie Vartan is a Bulgarian-born French pop singer and actress who became one of France’s most popular yé-yé idols in the 1960s.
  • D. Laeticia Hallyday
    Laeticia Hallyday is a French former model and philanthropist best known as the widow and longtime manager of rock icon Johnny Hallyday.
  • E. Mylène Farmer
    Mylène Farmer is a French singer-songwriter and producer renowned for her melancholic pop music, poetic lyrics, and visually striking, often controversial music videos.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623bba1881908440c92f08729ec1 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:34 p.m.