Triple

T9844906
Position Surface form Disambiguated ID Type / Status
Subject Breakthrough Prize in Mathematics E239316 entity
Predicate foundedBy P104 FINISHED
Object Yuri Milner E239313 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: Yuri Milner | Statement: [Breakthrough Prize in Mathematics, foundedBy, Yuri Milner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yuri Milner
Context triple: [Breakthrough Prize in Mathematics, foundedBy, Yuri Milner]
  • A. Yuri Milner chosen
    Yuri Milner is a Russian-Israeli billionaire technology investor and philanthropist known for backing major internet companies and creating high-profile science awards such as the Breakthrough Prizes.
  • B. Max Levchin
    Max Levchin is a Ukrainian-American computer scientist and entrepreneur best known as a co-founder of PayPal and a prominent figure in Silicon Valley’s fintech industry.
  • C. Nellie Levchin
    Nellie Levchin is the wife of Ukrainian-American entrepreneur and PayPal co-founder Max Levchin.
  • D. Anant Agarwal
    Anant Agarwal is a computer scientist and MIT professor best known as the founding CEO of edX, a major online learning platform.
  • E. Pavel Durov
    Pavel Durov is a Russian-born tech entrepreneur best known as the founder of the social networking site VKontakte and the encrypted messaging app Telegram.
  • 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_69ca84e3f0c48190ada72a65ebd50efd completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb35dc29c819080203be5b904dc9d completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1ead49b14819086a9bbd256f298a9 completed April 5, 2026, 4:53 a.m.
Created at: March 30, 2026, 8:33 p.m.