Triple

T17490214
Position Surface form Disambiguated ID Type / Status
Subject Johnny Hallyday E425883 entity
Predicate child P120 FINISHED
Object David Hallyday 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: David Hallyday | Statement: [Johnny Hallyday, child, David Hallyday]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Hallyday
Context triple: [Johnny Hallyday, child, David Hallyday]
  • A. David Hallyday chosen
    David Hallyday is a French singer-songwriter, musician, and racing driver, and the son of iconic entertainers Sylvie Vartan and Johnny Hallyday.
  • B. Johnny Hallyday
    Johnny Hallyday was a hugely popular French rock and pop singer and actor, often dubbed the "French Elvis" for his pivotal role in popularizing rock 'n' roll in France.
  • C. Michel Sardou
    Michel Sardou is a popular French singer and songwriter known for his powerful voice and numerous hit songs that have become classics of French chanson.
  • D. Jacques Dutronc
    Jacques Dutronc is a French singer-songwriter and actor known for his influential 1960s pop songs and acclaimed film performances.
  • E. Benoît Régent
    Benoît Régent was a French actor known for his supporting roles in European cinema, including a notable appearance in Krzysztof Kieślowski’s acclaimed film "Three Colors: Blue."
  • 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451d519488190a08da1b529c08445 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:48 a.m.