Triple

T20949097
Position Surface form Disambiguated ID Type / Status
Subject Gary Crosby E515930 entity
Predicate spouse P13 FINISHED
Object Marion Moses 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: Marion Moses | Statement: [Gary Crosby, spouse, Marion Moses]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Moses
Context triple: [Gary Crosby, spouse, Marion Moses]
  • A. Marion Moses chosen
    Marion Moses was the wife of American singer and actor Gary Crosby, son of legendary entertainer Bing Crosby.
  • B. Marion Edwards
    Marion Edwards was the wife of American film and television actor Robert Cummings.
  • C. Marion Hayden
    Marion Hayden is an American jazz bassist known for her work in the Detroit jazz scene and collaborations with numerous prominent artists.
  • D. Marion Marshall
    Marion Marshall was an American film actress who appeared in numerous Hollywood movies from the 1940s through the 1960s.
  • E. Marion Brown
    Marion Brown was an American jazz alto saxophonist and composer associated with the avant-garde and free jazz movements of the 1960s and beyond.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadc08148190b4ff710f94462a26 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 1:15 p.m.