Triple

T956698
Position Surface form Disambiguated ID Type / Status
Subject Stranger Things E20640 entity
Predicate director P255 FINISHED
Object Matt Duffer E112801 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: Matt Duffer | Statement: [Stranger Things, director, Matt Duffer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Duffer
Context triple: [Stranger Things, director, Matt Duffer]
  • A. Matt Duffer chosen
    Matt Duffer is an American television writer, director, and producer best known as one half of the Duffer Brothers, the duo behind the hit Netflix sci-fi horror series "Stranger Things."
  • B. Chris Weitz
    Chris Weitz is an American filmmaker, screenwriter, and producer known for directing films such as "About a Boy" and "The Golden Compass" and for co-directing "American Pie."
  • C. Daniel Pemberton
    Daniel Pemberton is a British composer known for his innovative and eclectic film scores across major Hollywood and independent productions.
  • D. Dan Scanlon
    Dan Scanlon is an American filmmaker and animator best known for his work as a director and writer at Pixar Animation Studios.
  • E. Craig Zadan
    Craig Zadan was an American film, television, and theater producer best known for his work on musical adaptations and live TV musicals, including projects like "Chicago" and NBC's live musical events.
  • 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_69a493b21f2881908132dcf45dcd2f36 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3f981bc819098125554eeeb6375 completed March 1, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac17016be0819097207669eae17490 completed March 7, 2026, 12:16 p.m.
Created at: March 1, 2026, 7:40 p.m.