Triple

T2760072
Position Surface form Disambiguated ID Type / Status
Subject Marvin Gaye E61196 entity
Predicate influenced P9 FINISHED
Object John Legend E196 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: John Legend | Statement: [Marvin Gaye, influenced, John Legend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Legend
Context triple: [Marvin Gaye, influenced, John Legend]
  • A. John Legend chosen
    John Legend is an American singer, songwriter, pianist, and actor known for his soulful R&B music and for being one of the few artists to achieve EGOT status (winning an Emmy, Grammy, Oscar, and Tony).
  • B. Brian McKnight
    Brian McKnight is an American R&B singer, songwriter, producer, and multi-instrumentalist known for his smooth vocals and romantic ballads.
  • C. Ne-Yo
    Ne-Yo is an American R&B singer, songwriter, and record producer known for hits like "So Sick" and for writing songs for numerous major artists.
  • D. Anthony Hamilton
    Anthony Hamilton is an American R&B and soul singer-songwriter known for his rich, raspy vocals and hits like "Charlene."
  • E. Luther Vandross
    Luther Vandross was an American R&B and soul singer, songwriter, and producer renowned for his smooth, emotive vocals and classic love ballads.
  • 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_69ab4b7bab6c8190a5c2efef19a8ef34 completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdd2121548190b96f174e6f61f9b5 completed March 7, 2026, 8:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69afbbe499148190902826dd769597d1 completed March 10, 2026, 6:36 a.m.
Created at: March 6, 2026, 9:57 p.m.