Triple

T20403183
Position Surface form Disambiguated ID Type / Status
Subject Maud Adams E500390 entity
Predicate spouse P13 FINISHED
Object Charles Rubin 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: Charles Rubin | Statement: [Maud Adams, spouse, Charles Rubin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Rubin
Context triple: [Maud Adams, spouse, Charles Rubin]
  • A. Charles Rubin chosen
    Charles Rubin is best known as the husband of Swedish actress and former Bond girl Maud Adams.
  • B. William Rosenberg
    William Rosenberg was an American entrepreneur best known for creating the coffee and doughnut chain that became Dunkin' Donuts.
  • C. Frank Waldman
    Frank Waldman was an American screenwriter best known for co-writing several of the Pink Panther films and other popular comedies of the mid-20th century.
  • D. Phil Rubinstein
    Phil Rubinstein is a fictional character portrayed by actor Andrew Robinson, likely appearing in a film or television production.
  • E. Robert B. Weide
    Robert B. Weide is an American film and television director, producer, and screenwriter best known for his work on the HBO series "Curb Your Enthusiasm" and various documentaries about comedians.
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6799080cc819096dc31f41d1d7b49 completed April 20, 2026, 7:08 p.m.
Created at: April 16, 2026, 11:29 a.m.