Triple

T2098410
Position Surface form Disambiguated ID Type / Status
Subject La voix E37035 entity
Predicate hasTitle P38 FINISHED
Object La voix E37035 NE FINISHED

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: La voix | Statement: [La voix, hasTitle, La voix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: La voix
Context triple: [La voix, hasTitle, La voix]
  • A. La voix chosen
    "La voix" is an operatic pop song performed by Swedish mezzo-soprano Malena Ernman as Sweden’s entry in the Eurovision Song Contest 2009.
  • B. Voices
    Voices is a sculptural artwork by Spanish artist Jaume Plensa, known for his large-scale, contemplative installations that explore the human figure, language, and spirituality.
  • C. The Voice from the Past
    "The Voice from the Past" is a humorous short story by P. G. Wodehouse featuring one of Mr Mulliner’s comic tall tales.
  • D. La voix humaine
    La voix humaine is a one-act monodrama opera by Francis Poulenc, based on Jean Cocteau’s play, depicting a woman’s emotional breakdown during a final phone call with her lover.
  • E. The Beloved
    The Beloved is a celebrated Pre-Raphaelite painting by Dante Gabriel Rossetti that portrays a richly adorned bride surrounded by attendants, exemplifying his fascination with beauty, color, and sensual symbolism.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abba9de75c81909770409b5ae62c24 completed March 7, 2026, 5:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae306386588190a1013c32a9b8e0c1 completed March 9, 2026, 2:28 a.m.
Created at: March 4, 2026, 7:43 p.m.