Triple

T3023494
Position Surface form Disambiguated ID Type / Status
Subject David Newman E82519 entity
Predicate relative P37 FINISHED
Object Lionel Newman E171030 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: Lionel Newman | Statement: [David Newman, relative, Lionel Newman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lionel Newman
Context triple: [David Newman, relative, Lionel Newman]
  • A. Lionel Newman chosen
    Lionel Newman was an American composer and conductor best known for his work in film and television music, including a long association with 20th Century Fox.
  • B. William Newman
    William Newman is a name shared by several notable individuals, including figures in fields such as computer science, acting, and academia.
  • C. Lionel Bender
    Lionel Bender was an American linguist known for his extensive research and classification work on African languages, particularly those in the Nilo-Saharan and Afroasiatic families.
  • D. Walter Newman
    Walter Newman was an American screenwriter known for his work on classic films such as "The Magnificent Seven" and "Cat Ballou."
  • E. Jerome Newman
    Jerome Newman was an American investor best known as the business partner of Benjamin Graham and co-founder of the influential Graham-Newman investment firm.
  • 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_69ad8b1fb34081908c1b873e2b7273e1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9ab8e0a48190ac79e674abd181cf completed March 8, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b224b2157881908d278be87bec5315 completed March 12, 2026, 2:28 a.m.
Created at: March 8, 2026, 3 p.m.