Triple

T15536629
Position Surface form Disambiguated ID Type / Status
Subject 1979 Australian Open – men’s singles E370361 entity
Predicate notablePlayer P304 FINISHED
Object John Sadri E1165912 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 Sadri | Statement: [1979 Australian Open – men’s singles, notablePlayer, John Sadri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Sadri
Context triple: [1979 Australian Open – men’s singles, notablePlayer, John Sadri]
  • A. John Sadri chosen
    John Sadri is a former American professional tennis player best known for his powerful serve and for reaching the final of the 1979 Australian Open.
  • B. Farhad Massoudi
    Farhad Massoudi is an entrepreneur best known as the founder of Tubi, a popular ad-supported video streaming service.
  • C. Shervin Alenabi
    Shervin Alenabi is an actor best known for his role in the espionage thriller television series "Tehran."
  • D. Bijan Davari
    Bijan Davari is an Iranian-American electrical engineer and IBM researcher known for his pioneering contributions to high-performance CMOS technology and microprocessor design.
  • E. Darius Alizadeh
    Darius Alizadeh is a character appearing in the James Bond continuation novel "Devil May Care" by Sebastian Faulks.
  • 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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e0442f3c688190a599165e526af2ed completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f2d4b1c81909ff876289db20803 completed May 9, 2026, 4:22 p.m.
Created at: April 10, 2026, 4:06 a.m.