Triple

T7027381
Position Surface form Disambiguated ID Type / Status
Subject Generalized Advantage Estimation E163182 entity
Predicate proposedBy P32 FINISHED
Object John Schulman E31866 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 Schulman | Statement: [Generalized Advantage Estimation, proposedBy, John Schulman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Schulman
Context triple: [Generalized Advantage Estimation, proposedBy, John Schulman]
  • A. John Schulman chosen
    John Schulman is an AI researcher and entrepreneur best known as a co-founder of OpenAI and a key contributor to advances in deep reinforcement learning and large language models.
  • B. Mark Shulman
    Mark Shulman is an American author best known for writing numerous children's books and humorous, educational titles for young readers.
  • C. Mark Schulman
    Mark Schulman is an American rock drummer and music educator best known for his work with major acts such as P!nk, Cher, and Foreigner.
  • D. Steven Baigelman
    Steven Baigelman is an American screenwriter and producer known for his work on biographical and crime dramas in film and television.
  • E. Johnny Gandelsman
    Johnny Gandelsman is a Grammy-winning violinist and producer known for his work with ensembles like Brooklyn Rider and the Silk Road Ensemble, as well as for his innovative solo projects.
  • 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_69c6885d691c81908cf7d31083113886 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1fee32081908eff988b18daa6d0 completed March 27, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c77588285481909799a2bb76921b9a completed March 28, 2026, 6:30 a.m.
Created at: March 27, 2026, 2:35 p.m.