Triple

T10997150
Position Surface form Disambiguated ID Type / Status
Subject Björn Andrésen E259903 entity
Predicate workedWith P398 FINISHED
Object Ari Aster E55433 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: Ari Aster | Statement: [Björn Andrésen, workedWith, Ari Aster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ari Aster
Context triple: [Björn Andrésen, workedWith, Ari Aster]
  • A. Ari Aster chosen
    Ari Aster is an American filmmaker and screenwriter best known for his unsettling, character-driven horror films such as "Hereditary" and "Midsommar."
  • B. Robert Eggers
    Robert Eggers is an American filmmaker known for his meticulously researched, atmospheric horror and period films such as "The Witch" and "The Lighthouse."
  • C. Mica Levi
    Mica Levi is an experimental British composer and musician known for their innovative film scores and genre-blurring work in contemporary classical and popular music.
  • D. Ti West
    Ti West is an American filmmaker and screenwriter best known for his work in independent horror cinema, including films like "The House of the Devil," "The Innkeepers," and the "X/Pearl/MaXXXine" trilogy.
  • E. James Vanderbilt
    James Vanderbilt is an American screenwriter and producer known for penning films such as "Zodiac," "The Amazing Spider-Man," and "White House Down."
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d796d20b448190958331705de3a9be completed April 9, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4418e52f8819096c75e6e866fecef completed April 19, 2026, 2:44 a.m.
Created at: April 8, 2026, 9:24 p.m.