Triple

T4743224
Position Surface form Disambiguated ID Type / Status
Subject Cookie Johnson E105296 entity
Predicate name P16 FINISHED
Object Cookie Johnson E105296 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: Cookie Johnson | Statement: [Cookie Johnson, name, Cookie Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cookie Johnson
Context triple: [Cookie Johnson, name, Cookie Johnson]
  • A. Cookie Johnson chosen
    Cookie Johnson is an American businesswoman, philanthropist, and HIV/AIDS advocate best known as the longtime wife of NBA legend Magic Johnson.
  • B. Jo Johnson
    Jo Johnson is a British Conservative politician and former Member of Parliament who has held ministerial roles, particularly in higher education and transport, and is the younger brother of former Prime Minister Boris Johnson.
  • C. Tee Hee Johnson
    Tee Hee Johnson is a henchman with a mechanical arm who serves as one of the main villains’ enforcers in the James Bond film "Live and Let Die."
  • D. Clay Johnson
    Clay Johnson is the nephew of fictional LAPD Deputy Chief Brenda Leigh Johnson on the television series "The Closer."
  • E. James Johnson
    James Johnson was a participant in the War of 1812, remembered for his role in the Battle of the Thames.
  • 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_69bd43ef87a48190a5bc3600711aa032 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64a85e9c81908e9c7bbbb998953e completed March 20, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be3a309a408190836c51d0fe85c5d8 completed March 21, 2026, 6:26 a.m.
Created at: March 20, 2026, 1:19 p.m.