Triple

T2771095
Position Surface form Disambiguated ID Type / Status
Subject Cobra E61456 entity
Predicate starring P1507 FINISHED
Object Brigitte Nielsen E66205 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: Brigitte Nielsen | Statement: [Cobra, starring, Brigitte Nielsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brigitte Nielsen
Context triple: [Cobra, starring, Brigitte Nielsen]
  • A. Brigitte Nielsen chosen
    Brigitte Nielsen is a Danish actress, model, and television personality known for her roles in 1980s action films and her high-profile marriage to Sylvester Stallone.
  • B. Regine Olsen
    Regine Olsen was a 19th-century Danish woman best known as the fiancée and muse of philosopher Søren Kierkegaard, whose broken engagement to her profoundly shaped his life and writings.
  • C. Sara Esberg
    Sara Esberg is a television producer known for her executive production work on series such as the psychological horror show "Swarm."
  • D. Brigitte Herbst
    Brigitte Herbst was the wife of Hans Frank, a prominent Nazi official and Governor-General of occupied Poland during World War II.
  • E. Charlotte Bruus Christensen
    Charlotte Bruus Christensen is a Danish cinematographer known for her atmospheric, naturalistic visual style in films such as "A Quiet Place" and "Fences."
  • 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_69ab4b7cd13481909174bca9809ed259 completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdd6a23208190ba94c9a9f601a042 completed March 7, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc05061808190abe709eff7a8c986 completed March 10, 2026, 6:55 a.m.
Created at: March 6, 2026, 9:57 p.m.