Triple

T19351202
Position Surface form Disambiguated ID Type / Status
Subject Grand Theft Auto E484022 entity
Predicate starring P1507 FINISHED
Object Marion Ross 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 Ross | Statement: [Grand Theft Auto, starring, Marion Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Ross
Context triple: [Grand Theft Auto, starring, Marion Ross]
  • A. Marion Ross chosen
    Marion Ross is an American actress best known for playing matriarch Marion Cunningham on the classic television sitcom "Happy Days."
  • B. Loretta Swit
    Loretta Swit is an American actress best known for her Emmy-winning role as Major Margaret "Hot Lips" Houlihan on the television series M*A*S*H.
  • C. Jill Eikenberry
    Jill Eikenberry is an American actress best known for her Emmy-nominated role as attorney Ann Kelsey on the television series "L.A. Law."
  • D. Mary Tyler Moore
    Mary Tyler Moore was an influential American actress and television icon best known for redefining the portrayal of independent working women through her roles on "The Dick Van Dyke Show" and "The Mary Tyler Moore Show."
  • E. Tina Yothers
    Tina Yothers is an American actress best known for playing Jennifer Keaton on the 1980s sitcom "Family Ties."
  • 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_69d8e8d244f8819080eb1f3491300db2 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e61904a878819084d58ed3b7d8a978 completed April 20, 2026, 12:16 p.m.
Created at: April 10, 2026, 1:34 p.m.