Triple

T20444808
Position Surface form Disambiguated ID Type / Status
Subject Maybelle Carter E501489 entity
Predicate relative P37 FINISHED
Object Sara Carter 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: Sara Carter | Statement: [Maybelle Carter, relative, Sara Carter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Carter
Context triple: [Maybelle Carter, relative, Sara Carter]
  • A. Sara Carter chosen
    Sara Carter was a pioneering American country and folk musician best known as a founding member and lead vocalist of the influential Carter Family.
  • B. Elizabeth Clinch
    Elizabeth Clinch is known primarily as the wife and partner of American mountaineer and expedition leader Nicholas Clinch.
  • C. Dixie Pearl Followill
    Dixie Pearl Followill is the daughter of American model Lily Aldridge and Kings of Leon frontman Caleb Followill.
  • D. Juanita Cowart
    Juanita Cowart is an American singer best known as an original member of the Motown girl group The Marvelettes, who recorded the hit "Please Mr. Postman."
  • E. Shemekia Copeland
    Shemekia Copeland is an acclaimed American blues singer known for her powerful vocals and contemporary take on traditional blues.
  • 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_69e0b4ac0a1c81908845d0f8a56abce8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e68cfca4788190ad57ecb504f54d11 completed April 20, 2026, 8:30 p.m.
Created at: April 16, 2026, 11:32 a.m.