Triple

T16411854
Position Surface form Disambiguated ID Type / Status
Subject Thierry Arbogast E398585 entity
Predicate workedOn P3 FINISHED
Object Anna
"Anna" is a 2019 action-thriller film written and directed by Luc Besson, centered on a highly skilled female assassin leading a double life.
E1212740 NE FINISHED

How this triple was built (4 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: Anna | Statement: [Thierry Arbogast, workedOn, Anna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna
Context triple: [Thierry Arbogast, workedOn, Anna]
  • A. Anna
    Anna is the given name of Anna Murray Douglass, an African American abolitionist and the first wife of Frederick Douglass.
  • B. Anna
    Anna is an actress known for portraying the ambitious and manipulative Lady Macbeth in a production of Shakespeare’s tragedy "Macbeth."
  • C. Anna
    Anna is a biblical figure in the Book of Tobit, known as Tobit's wife and the mother of Tobias.
  • D. Anna
    Anna is a woman whose full name is Mrs. Anna Smith.
  • E. Anna
    Anna of Moscow was a medieval Russian noblewoman and princess associated with the ruling dynasties of Muscovy.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Anna
Triple: [Thierry Arbogast, workedOn, Anna]
Generated description
"Anna" is a 2019 action-thriller film written and directed by Luc Besson, centered on a highly skilled female assassin leading a double life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anna
Target entity description: "Anna" is a 2019 action-thriller film written and directed by Luc Besson, centered on a highly skilled female assassin leading a double life.
  • A. Anna
    Anna is a key female resistance fighter in the World War II adventure film "The Guns of Navarone," whose complex loyalties and actions significantly impact the mission’s outcome.
  • B. Anna
    Anna is a central female character in the comedy Western film "A Million Ways to Die in the West," portrayed as a sharp-shooting, quick-witted woman who helps the protagonist toughen up in the dangerous frontier.
  • C. Anna
    Anna is a character from the "Predator" franchise, appearing as one of the human figures caught up in the deadly encounters with the extraterrestrial hunter.
  • D. Anna
    Anna is the given first name of Anny Ondra, the Czech-Austrian film actress best known for her work in early European cinema and Alfred Hitchcock’s films.
  • E. Anna
    Anna is a fictional character played by British actress Naomi Ackie, known for her work in film and television.
  • F. None of above. chosen

Provenance (5 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_69d87f2950248190bc8ad9b9bebdc8c8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32874a0cc8190874aea10b1d13004 completed April 18, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00457d9f4081908a5f28eeafc44695 completed May 10, 2026, 8:44 a.m.
NEDg Description generation batch_6a00469f5d8081908c21fc30dcb5d5b8 completed May 10, 2026, 8:49 a.m.
NED2 Entity disambiguation (via description) batch_6a0047322384819082a95f9a6f5a53fc completed May 10, 2026, 8:52 a.m.
Created at: April 10, 2026, 5:09 a.m.