Triple

T21380246
Position Surface form Disambiguated ID Type / Status
Subject Donald Tokowitz E527331 entity
Predicate alsoKnownAs P39 FINISHED
Object Donald Sterling 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: Donald Sterling | Statement: [Donald Tokowitz, alsoKnownAs, Donald Sterling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donald Sterling
Context triple: [Donald Tokowitz, alsoKnownAs, Donald Sterling]
  • A. Donald Sterling chosen
    Donald Sterling is an American real estate mogul and former NBA team owner best known for his controversial tenure and lifetime ban from the league following the release of racist remarks.
  • B. Leon Black
    Leon Black is an American billionaire investor and co-founder of the private equity firm Apollo Global Management.
  • C. Whitney Kroenke
    Whitney Kroenke is an American philanthropist and film producer best known as the co-founder of the global music and arts nonprofit initiative Playing for Change.
  • D. Stan Kroenke
    Stan Kroenke is an American billionaire real estate and sports mogul who owns multiple major professional teams, including the NFL’s Los Angeles Rams.
  • E. Ann Walton Kroenke
    Ann Walton Kroenke is an American billionaire heiress to the Walmart fortune and a prominent sports team owner.
  • 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_69e0b51f363c8190944000ab5523b02b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0cdab8c8190a7eebe6e5961ee75 completed April 22, 2026, 11:28 a.m.
Created at: April 16, 2026, 5:11 p.m.