Triple

T13473087
Position Surface form Disambiguated ID Type / Status
Subject Bruno Delbonnel E318178 entity
Predicate notableWork P4 FINISHED
Object Across the Universe E557293 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: Across the Universe | Statement: [Bruno Delbonnel, notableWork, Across the Universe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Across the Universe
Context triple: [Bruno Delbonnel, notableWork, Across the Universe]
  • A. Across the Universe chosen
    Across the Universe is a 2007 musical romantic drama film that weaves a love story through imaginative, visually rich sequences set to songs by The Beatles.
  • B. Starboy
    "Starboy" is a 2016 hit single by The Weeknd featuring Daft Punk, known for its dark, moody production and exploration of fame and identity.
  • C. Starboy
    Starboy is the popular stage name and persona of Nigerian Afrobeats singer and songwriter Wizkid, under which he has released several hit songs and projects.
  • D. Somewhere
    "Somewhere" is a track by the American rock band Soundgarden from their influential 1991 album *Badmotorfinger*.
  • E. Somewhere
    Somewhere is a 2010 introspective drama film written and directed by Sofia Coppola that follows a disaffected Hollywood actor reconnecting with his young daughter.
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf2447bc81908baf1f4b55095144 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7462d97688190b5b817fff5973ceb completed May 3, 2026, 12:57 p.m.
Created at: April 9, 2026, 9:42 p.m.