Triple

T4651165
Position Surface form Disambiguated ID Type / Status
Subject Tom B. Brown E102297 entity
Predicate hasCoAuthor P2389 FINISHED
Object Ariel Herbert-Voss
Ariel Herbert-Voss is a machine learning researcher known for her work at OpenAI on large language models and AI safety.
E457865 NE FINISHED

How this triple was built (4 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, hasCoAuthor, 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, hasCoAuthor, Ariel Herbert-Voss]
  • A. Tessa Berens
    Tessa Berens is a fictional character from the work titled "The Silence."
  • B. Leilani Sarelle
    Leilani Sarelle is an American actress best known for her role as Roxy in the 1992 thriller film "Basic Instinct."
  • C. Alexia Barroso
    Alexia Barroso is the stepdaughter of actor Matt Damon, known for largely maintaining a private life outside of the public spotlight.
  • D. Everly Carganilla
    Everly Carganilla is a young American child actress known for roles in film and television, including the Netflix series "The Chair."
  • E. Lara Lea Yunaska
    Lara Lea Yunaska is an American television producer and political figure best known as Lara Trump, the wife of Eric Trump and a prominent surrogate and adviser in Donald Trump’s political campaigns.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ariel Herbert-Voss
Triple: [Tom B. Brown, hasCoAuthor, Ariel Herbert-Voss]
Generated description
Ariel Herbert-Voss is a machine learning researcher known for her work at OpenAI on large language models and AI safety.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ariel Herbert-Voss
Target entity description: Ariel Herbert-Voss is a machine learning researcher known for her work at OpenAI on large language models and AI safety.
  • A. Tessa Berens
    Tessa Berens is a fictional character from the work titled "The Silence."
  • B. Leilani Sarelle
    Leilani Sarelle is an American actress best known for her role as Roxy in the 1992 thriller film "Basic Instinct."
  • C. Alexia Barroso
    Alexia Barroso is the stepdaughter of actor Matt Damon, known for largely maintaining a private life outside of the public spotlight.
  • D. Everly Carganilla
    Everly Carganilla is a young American child actress known for roles in film and television, including the Netflix series "The Chair."
  • E. Lara Lea Yunaska
    Lara Lea Yunaska is an American television producer and political figure best known as Lara Trump, the wife of Eric Trump and a prominent surrogate and adviser in Donald Trump’s political campaigns.
  • F. None of above. chosen

Provenance (5 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_69bd43d71a308190afea7280841b0de8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6c3d1cb88190a42919dcbfe2568c completed March 20, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfae7636881908244b86cba1c66b7 completed March 21, 2026, 1:56 a.m.
NEDg Description generation batch_69bdfbc12acc8190b8116a6003abb3e3 completed March 21, 2026, 2 a.m.
NED2 Entity disambiguation (via description) batch_69bdfc44536c8190a71e52b0690a7570 completed March 21, 2026, 2:02 a.m.
Created at: March 20, 2026, 1:14 p.m.