Triple

T20619997
Position Surface form Disambiguated ID Type / Status
Subject People Like Us E506673 entity
Predicate stars P1956 FINISHED
Object Mark Duplass 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: Mark Duplass | Statement: [People Like Us, stars, Mark Duplass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Duplass
Context triple: [People Like Us, stars, Mark Duplass]
  • A. Mark Duplass chosen
    Mark Duplass is an American actor, writer, director, and producer known for his work in independent film and television, including co-creating the HBO series "Togetherness" and starring in numerous mumblecore and comedy-dramas.
  • B. Jay Duplass
    Jay Duplass is an American filmmaker and actor known for his work in independent cinema and television, often collaborating with his brother Mark Duplass.
  • C. Lawrence Duplass
    Lawrence Duplass is a member of the Duplass family, related to American filmmaker and actor Jay Duplass.
  • D. Paul Dano
    Paul Dano is an American actor and filmmaker known for his intense, often offbeat performances in films such as "There Will Be Blood," "Little Miss Sunshine," and "Prisoners."
  • E. Michael Pitt
    Michael Pitt is an American actor and musician best known for his roles in films like "The Dreamers" and "Funny Games" and for his prominent television work in series such as "Boardwalk Empire" and "Hannibal."
  • 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_69e0b4bc90988190ac360aaf645efc1d completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6abe0e22c81909f6efe21518e33f0 completed April 20, 2026, 10:42 p.m.
Created at: April 16, 2026, 11:41 a.m.