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.