Triple

T15046750
Position Surface form Disambiguated ID Type / Status
Subject Come Over E379247 entity
Predicate writer P1360 FINISHED
Object John Stephens E1118698 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 Stephens | Statement: [Come Over, writer, John Stephens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Stephens
Context triple: [Come Over, writer, John Stephens]
  • A. John Stephens chosen
    John Stephens, better known by his stage name John Legend, is an American singer, songwriter, and pianist renowned for his soulful R&B music and numerous Grammy-winning hits.
  • B. John Stephens
    John Stephens is an author best known for writing the children's fantasy novel "The Emerald Atlas" and its sequels in the Books of Beginning series.
  • C. John Stephens
    John Stephens is an American local politician who has served as the mayor of Costa Mesa, California.
  • D. Stephen P. Maran
    Stephen P. Maran is an American astronomer and science communicator known for his work with NASA and for authoring popular astronomy books such as "Astronomy for Dummies."
  • E. Michael L. Riordan
    Michael L. Riordan is an American physician and entrepreneur best known as the founding CEO of the biopharmaceutical company Gilead Sciences.
  • 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69deda8e64e48190873104a02a676ff3 completed April 15, 2026, 12:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9de73614819098b7a88624407d0e completed May 9, 2026, 2:37 a.m.
Created at: April 10, 2026, 3 a.m.