Triple

T20667798
Position Surface form Disambiguated ID Type / Status
Subject George Mallory E507937 entity
Predicate spouse P13 FINISHED
Object Ruth Mallory 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: Ruth Mallory | Statement: [George Mallory, spouse, Ruth Mallory]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Mallory
Context triple: [George Mallory, spouse, Ruth Mallory]
  • A. Ruth Mallory chosen
    Ruth Mallory was the wife of British mountaineer George Mallory, remembered largely for her connection to his ill-fated Everest expeditions and the poignant letters they exchanged.
  • B. Ruth Henshaw
    Ruth Henshaw is a fictional character portrayed by American actress Frances Rafferty, likely in mid-20th-century film or television.
  • C. Evelyn Draper
    Evelyn Draper is the obsessive and increasingly dangerous female stalker in the 1971 psychological thriller film "Play Misty for Me."
  • D. Ruth Harper
    Ruth Harper was the wife of influential American sociologist C. Wright Mills, known primarily in relation to his personal and intellectual biography.
  • E. Ruth Benjamin
    Ruth Benjamin was the wife of American actor and director Jerry Paris, known for his work on The Dick Van Dyke Show and various television comedies.
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5c4c4608190ae17da4a59e5ae80 completed April 20, 2026, 11:24 p.m.
Created at: April 16, 2026, 11:44 a.m.