Triple

T9689900
Position Surface form Disambiguated ID Type / Status
Subject Les Troyens E234509 entity
Predicate character P662 FINISHED
Object Anna
Anna is a supporting character in Hector Berlioz’s grand opera *Les Troyens*, typically portrayed as Dido’s loyal sister and confidante.
 E815628 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: [Les Troyens, character, Anna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Anna
Context triple: [Les Troyens, character, 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 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 the given name of pioneering Chinese American actress Anna May Wong, a trailblazing early Hollywood star and fashion icon.
  • D. Anna
    Anna is a character from the video game "Surfacing," likely serving as a key figure in the game's narrative or player interactions.
  • E. Anna
    Anna is a feminine given name of Hebrew origin meaning "grace" or "favor," widely used across many cultures and languages.
  • 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: [Les Troyens, character, Anna]
Generated description
Anna is a supporting character in Hector Berlioz’s grand opera *Les Troyens*, typically portrayed as Dido’s loyal sister and confidante.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Anna
Target entity description: Anna is a supporting character in Hector Berlioz’s grand opera *Les Troyens*, typically portrayed as Dido’s loyal sister and confidante.
  • 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 biblical figure in the Book of Tobit, known as Tobit's wife and the mother of Tobias.
  • C. Anna
    Anna is the tragic, aristocratic heroine of Leo Tolstoy’s novel "Anna Karenina," whose passionate affair and struggle against societal norms lead to her downfall.
  • D. Anna
    Anna is a spirited and optimistic princess from Disney's animated film "Frozen," known for her bravery, loyalty, and deep love for her sister Elsa.
  • E. 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.
  • 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_69ca84ca73208190957a900c8543bdcc completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9d02b20881909d7c0d5d6aaafcb0 completed April 1, 2026, 10:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1911427d48190855506ab61f8a2ce completed April 4, 2026, 10:30 p.m.
NEDg Description generation batch_69d193a5cdac8190b84564f397d00124 completed April 4, 2026, 10:41 p.m.
NED2 Entity disambiguation (via description) batch_69d19457c6488190a7bc72e1a27c088a completed April 4, 2026, 10:44 p.m.
Created at: March 30, 2026, 8:17 p.m.