Triple

T6868474
Position Surface form Disambiguated ID Type / Status
Subject Team Downey E158476 entity
Predicate coFounder P2835 FINISHED
Object Susan Downey E158476 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: Susan Downey | Statement: [Team Downey, coFounder, Susan Downey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Downey
Context triple: [Team Downey, coFounder, Susan Downey]
  • A. Susan Downey chosen
    Susan Downey is an American film producer and co-founder of Team Downey, known for her work on genre films and collaborations with her husband Robert Downey Jr.
  • B. Deborah Downey
    Deborah Downey is an American actress and singer best known for her guest appearance as a space hippie in the original Star Trek series episode "The Way to Eden."
  • C. Sharon Downey
    Sharon Downey is an individual associated with the use of the name or term "Downey," likely as a personal or family surname.
  • D. Claudia Edwards Downey
    Claudia Edwards Downey was the first wife of American U-2 pilot Francis Gary Powers, known for her troubled marriage to him during the Cold War era.
  • E. Lisa Blount
    Lisa Blount was an American actress and producer best known for her acclaimed supporting role in the film "An Officer and a Gentleman."
  • 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_69c68831e3648190a643c328122e4d43 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d8a793a481909340239c065393a4 completed March 27, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c922a0d2688190982714e2e409465d completed March 29, 2026, 1:01 p.m.
Created at: March 27, 2026, 2:21 p.m.