Triple

T7850136
Position Surface form Disambiguated ID Type / Status
Subject Mabel Beckman E182024 entity
Predicate spouse P13 FINISHED
Object Arnold O. Beckman E73549 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: Arnold O. Beckman | Statement: [Mabel Beckman, spouse, Arnold O. Beckman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arnold O. Beckman
Context triple: [Mabel Beckman, spouse, Arnold O. Beckman]
  • A. Arnold O. Beckman chosen
    Arnold O. Beckman was an American chemist, inventor, and philanthropist best known for developing the pH meter and founding Beckman Instruments, which significantly advanced scientific instrumentation.
  • B. Frederick Seitz
    Frederick Seitz was an influential American physicist and solid-state physics pioneer who served as president of the National Academy of Sciences and Rockefeller University.
  • C. Melvin Wydler
    Melvin Wydler was a U.S. Congressman whose legislative work on technology and innovation policy led to a federal law being named in his honor.
  • D. Albert Schatz
    Albert Schatz was an American microbiologist best known for co-discovering the antibiotic streptomycin, the first effective treatment for tuberculosis.
  • E. Raymond W. Stark
    Raymond W. Stark was an American film producer known for backing numerous successful Hollywood movies from the 1960s through the 1990s.
  • 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_69ca82869ee08190b8f9040dbc2c0467 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb18e989ac819090e459b77d8932d3 completed March 31, 2026, 12:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b0515c08190b866a39749d54849 completed March 31, 2026, 5:26 a.m.
Created at: March 30, 2026, 4:50 p.m.