Triple

T19634091
Position Surface form Disambiguated ID Type / Status
Subject Tom B. Brown E471343 entity
Predicate coAuthorWith P398 FINISHED
Object Ariel Herbert-Voss 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: Ariel Herbert-Voss | Statement: [Tom B. Brown, coAuthorWith, Ariel Herbert-Voss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ariel Herbert-Voss
Context triple: [Tom B. Brown, coAuthorWith, Ariel Herbert-Voss]
  • A. Ariel Herbert-Voss chosen
    Ariel Herbert-Voss is a machine learning researcher known for her work at OpenAI on large language models and AI safety.
  • B. Ariel Shepherd-Oppenheim
    Ariel Shepherd-Oppenheim is an American writer and the daughter of actress Cybill Shepherd.
  • C. Ariel Vromen
    Ariel Vromen is an Israeli film director, screenwriter, and producer best known for directing crime and thriller films such as "The Iceman" and "Criminal."
  • D. Ariel Moore
    Ariel Moore is the rebellious and spirited teenage daughter of a strict minister in the musical film "Footloose," whose desire for freedom and dancing drives much of the story’s conflict.
  • E. Ariel Nicoli
    Ariel Nicoli is one of the children of South African supermodel Candice Swanepoel.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64104ff2881908fec49b7fba5a2e6 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.