Triple

T17073979
Position Surface form Disambiguated ID Type / Status
Subject Kim Novak E414298 entity
Predicate spouse P13 FINISHED
Object Richard Johnson E327740 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: Richard Johnson | Statement: [Kim Novak, spouse, Richard Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Johnson
Context triple: [Kim Novak, spouse, Richard Johnson]
  • A. Richard Johnson chosen
    Richard Johnson was a British actor known for his work in mid-20th-century film and television, including prominent roles in war and horror movies.
  • B. Richard Johnson
    Richard Johnson is an Australian architect best known for designing prominent public and cultural buildings, including major national institutions.
  • C. Richard Johnson
    Richard Johnson is the husband of Francesca Johnson, a character in the romantic drama "The Bridges of Madison County."
  • D. Bruce Douglas Johnson
    Bruce Douglas Johnson is a cinematographer best known for his work on the stoner comedy film "Harold & Kumar Go to White Castle."
  • E. Warren Seymour Johnson
    Warren Seymour Johnson was an American inventor and entrepreneur best known for pioneering automatic temperature control systems and founding the company that became Johnson Controls.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbc3b69c819093b32da3998eed46 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012ede108881909ddd0455be53ffac completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:34 a.m.