Triple

T16673734
Position Surface form Disambiguated ID Type / Status
Subject Half-Breed E405165 entity
Predicate signatureSongOf P491 FINISHED
Object Cher E92362 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: Cher | Statement: [Half-Breed, signatureSongOf, Cher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cher
Context triple: [Half-Breed, signatureSongOf, Cher]
  • A. Cher
    Cher is a department in central France, named after the Cher River and known for its historic towns, vineyards, and agricultural landscapes.
  • B. Cher chosen
    Cher is an American singer, actress, and pop culture icon known for her distinctive contralto voice, decades-spanning career, and hits like "Believe" and "If I Could Turn Back Time."
  • C. Cher
    Cher is the four-letter ISO 15924 script code that designates the Cherokee syllabary writing system.
  • D. Barbara West
    Barbara West is an actress known for her role in the acclaimed Australian psychological horror film "The Babadook."
  • E. Cyndi Grecco
    Cyndi Grecco is an American singer best known for performing the upbeat 1970s television theme song "Making Our Dreams Come True" from the sitcom Laverne & Shirley.
  • 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_69d8838c28748190b3f5967c743940ab completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37d6904008190a79ab30b6d9ccae9 completed April 18, 2026, 12:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a51169b881909216ab1055752978 completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 5:19 a.m.