Triple

T13384423
Position Surface form Disambiguated ID Type / Status
Subject The Neon Demon E319402 entity
Predicate producer P490 FINISHED
Object Lene Børglum E913244 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: Lene Børglum | Statement: [The Neon Demon, producer, Lene Børglum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lene Børglum
Context triple: [The Neon Demon, producer, Lene Børglum]
  • A. Lene Børglum chosen
    Lene Børglum is a Danish film producer known for her collaborations with director Nicolas Winding Refn on several acclaimed independent films.
  • B. Lene Christensen
    Lene Christensen is a Danish professional football goalkeeper known for playing in the Danish national team setup and in top-tier European women’s club football.
  • C. Birgitte Hjort Sørensen
    Birgitte Hjort Sørensen is a Danish actress known for her roles in the political drama series "Borgen" and various international film and television productions.
  • D. Lene Andersen
    Lene Andersen is a Danish author and futurist known for her work on democracy, ethics, and societal development.
  • E. Vibeke Windeløv
    Vibeke Windeløv is a Danish film producer best known for her long-time collaboration with director Lars von Trier on several acclaimed art-house films.
  • 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_69d806b886bc8190b676e7768b8e01c5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dadce80158819082156eaeaeda3bd8 completed April 11, 2026, 11:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7268cf04c8190a35fd48ce81c149e completed May 3, 2026, 10:42 a.m.
Created at: April 9, 2026, 9:33 p.m.