Triple

T14969671
Position Surface form Disambiguated ID Type / Status
Subject Marion Marshall E373282 entity
Predicate relative P37 FINISHED
Object Mark Donen E274414 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: Mark Donen | Statement: [Marion Marshall, relative, Mark Donen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Donen
Context triple: [Marion Marshall, relative, Mark Donen]
  • A. Ron Gans
    Ron Gans was an American voice actor best known for his work in animation and television, including voicing characters in the Winnie the Pooh franchise.
  • B. Lee Zahler
    Lee Zahler was an American film composer and musical director known for scoring numerous serials and B-movies during the 1930s and 1940s.
  • C. Joshua Donen chosen
    Joshua Donen is an American film and television producer known for working on projects such as the Western film "The Quick and the Dead" and various high-profile genre productions.
  • D. Michael Seitzman
    Michael Seitzman is an American screenwriter and producer known for his work on films such as "North Country" and for creating and producing several television series.
  • E. John Hyams
    John Hyams is an American film and television director, producer, and screenwriter known for his work in action and horror, including the series "Black Summer" and entries in the "Universal Soldier" franchise.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e59a7c8190a1634a706ea68fda completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9692e4fc8190a1194a41fc8a832c completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:49 a.m.