Triple

T20147814
Position Surface form Disambiguated ID Type / Status
Subject Anita Ekberg E491350 entity
Predicate spouse P13 FINISHED
Object Rik Van Nutter 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: Rik Van Nutter | Statement: [Anita Ekberg, spouse, Rik Van Nutter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rik Van Nutter
Context triple: [Anita Ekberg, spouse, Rik Van Nutter]
  • A. Rik Van Nutter chosen
    Rik Van Nutter was an American actor best known for playing CIA agent Felix Leiter in the James Bond film "Thunderball" (1965).
  • B. Greg Rikaart
    Greg Rikaart is an American television actor best known for his long-running role as Kevin Fisher on the soap opera "The Young and the Restless."
  • C. Nick Schenk
    Nick Schenk is an American screenwriter best known for writing the Clint Eastwood film "Gran Torino."
  • D. Rick Janssen
    Rick Janssen is the main test subject and soldier in the science fiction film "The Titan," undergoing a radical experiment to adapt humans for life on Saturn’s moon Titan.
  • E. Steven Vandeput
    Steven Vandeput is a Belgian politician who has served as the mayor of Hasselt and is known for his role in national and local government.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667a0075c8190a5c4de53a0caa7f6 completed April 20, 2026, 5:51 p.m.
Created at: April 11, 2026, 11:33 p.m.