Triple

T18657398
Position Surface form Disambiguated ID Type / Status
Subject Royal Machines E456102 entity
Predicate hasFormerMember P1168 FINISHED
Object Franky Perez 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: Franky Perez | Statement: [Royal Machines, hasFormerMember, Franky Perez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franky Perez
Context triple: [Royal Machines, hasFormerMember, Franky Perez]
  • A. Franky Perez chosen
    Franky Perez is an American rock singer and guitarist known for his solo work and collaborations with various hard rock and metal bands.
  • B. Rico Diaz
    Rico Diaz is a fictional funeral director and co-owner of Fisher & Diaz Funeral Home in the television series "Six Feet Under."
  • C. Mickey Rivera
    Mickey Rivera is a notable graduate of Westminster Christian School recognized for his achievements after attending the Miami-based private Christian institution.
  • D. Felix Rodriguez
    Felix Rodriguez is a Cuban-American former CIA operative known for his involvement in covert Cold War operations, including the Bay of Pigs invasion and the capture of Che Guevara.
  • E. Rudy Reyes
    Rudy Reyes is a former U.S. Marine turned actor and military advisor best known for portraying himself in the HBO miniseries "Generation Kill."
  • 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_69d8d38ea1e88190997e9b231190ba6f completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e550864b0481909e59fbcc79fda839 completed April 19, 2026, 10 p.m.
Created at: April 10, 2026, 11:48 a.m.