Triple

T11773321
Position Surface form Disambiguated ID Type / Status
Subject The Devil's Advocate E279954 entity
Predicate starring P1507 FINISHED
Object Connie Nielsen E153176 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: Connie Nielsen | Statement: [The Devil's Advocate, starring, Connie Nielsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Connie Nielsen
Context triple: [The Devil's Advocate, starring, Connie Nielsen]
  • A. Connie Nielsen chosen
    Connie Nielsen is a Danish actress best known for her roles in films such as "Gladiator" and "Wonder Woman."
  • B. Jaimie Alexander
    Jaimie Alexander is an American actress best known for her role as the Asgardian warrior Lady Sif in the Marvel Cinematic Universe and for starring in the TV series "Blindspot."
  • C. AnnaSophia Robb
    AnnaSophia Robb is an American actress known for her roles in films such as "Soul Surfer" and "Bridge to Terabithia," as well as the TV series "The Carrie Diaries."
  • D. Kathleen Robertson
    Kathleen Robertson is a Canadian actress known for her roles in television series like "Beverly Hills, 90210" and "Boss," as well as various film and genre projects.
  • E. Thandie Newton
    Thandie Newton is a British actress acclaimed for her powerful performances in film and television, including roles in "Crash," "Westworld," and numerous other high-profile productions.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a55dfa088190a59b35d0247225e3 completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f0909969e481908d836f912b5af5bf completed April 28, 2026, 10:48 a.m.
Created at: April 8, 2026, 9:41 p.m.