Triple

T10906716
Position Surface form Disambiguated ID Type / Status
Subject My Week with Marilyn E257590 entity
Predicate editor P1954 FINISHED
Object Adam Recht E257590 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: Adam Recht | Statement: [My Week with Marilyn, editor, Adam Recht]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adam Recht
Context triple: [My Week with Marilyn, editor, Adam Recht]
  • A. Adam Recht chosen
    Adam Recht is a film editor known for his work on the biographical drama "My Week with Marilyn."
  • B. Adam Meiks
    Adam Meiks is a central character in the psychological horror film "Frailty," whose troubled past and family’s fanatical religious visions drive the movie’s mystery and moral ambiguity.
  • C. Adam Reta
    Adam Reta is a prominent Ethiopian writer recognized for his significant contributions to modern Ethiopian literature.
  • D. Adam Ruzek
    Adam Ruzek is a fictional undercover specialist and member of the Intelligence Unit on the television drama series "Chicago P.D."
  • E. Adam Senn
    Adam Senn is an American model and actor best known for his role as professional basketball player Zero on the VH1 drama series "Hit the Floor."
  • 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_69d6aa8550c8819095508a2ed9acf3db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7706679b48190a1f29fc64fe8a334 completed April 9, 2026, 9:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69e155454890819087028a72ac2be8de completed April 16, 2026, 9:31 p.m.
Created at: April 8, 2026, 9:22 p.m.