Triple

T689364
Position Surface form Disambiguated ID Type / Status
Subject Son of Kong E13356 entity
Predicate screenwriter P2831 FINISHED
Object Ruth Rose E55210 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: Ruth Rose | Statement: [Son of Kong, screenwriter, Ruth Rose]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Rose
Context triple: [Son of Kong, screenwriter, Ruth Rose]
  • A. Ruth Rose chosen
    Ruth Rose was an American screenwriter best known for co-writing the classic 1933 monster film "King Kong."
  • B. Ruth Snyder
    Ruth Snyder was an American woman infamously executed in 1928 for the murder of her husband, a case that became notorious due to a secretly photographed image of her electrocution published in the press.
  • C. Ruth Elizabeth Davis
    Ruth Elizabeth Davis, better known as Bette Davis, was a legendary American film actress renowned for her intense performances and pioneering portrayals of complex, independent women in Hollywood’s Golden Age.
  • D. Dorothy Revier
    Dorothy Revier was an American silent and early sound film actress known for her roles in adventure and drama films of the 1920s and 1930s.
  • E. Rhoda Williams
    Rhoda Williams was an American actress and voice artist best known for her work in mid-20th-century film and radio, including voice roles in classic animated features.
  • 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a09669e4819089753204772e1fdd completed March 1, 2026, 8:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae02eda1048190b5452b849315863f completed March 8, 2026, 11:14 p.m.
Created at: March 1, 2026, 7:36 p.m.