Triple

T2082621
Position Surface form Disambiguated ID Type / Status
Subject Frozen Ever After E45276 entity
Predicate featuresCharacter P626 FINISHED
Object Anna
Anna is a main protagonist from Disney's Frozen franchise, known as the optimistic and fearless princess of Arendelle and sister of Queen Elsa.
 E198466 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: [Frozen Ever After, featuresCharacter, Anna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Anna
Context triple: [Frozen Ever After, featuresCharacter, Anna]
  • A. Anna
    Anna is the given first name of Eleanor Roosevelt, the influential former First Lady of the United States and human rights advocate.
  • B. Anna
    Anna is the given name of Anna Murray Douglass, an African American abolitionist and the first wife of Frederick Douglass.
  • C. 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.
  • D. Anna
    Anna is the given name of Anna Laetitia Barbauld, an influential 18th–19th century English poet, essayist, and children's author.
  • E. Anna
    Anna is the given name of pioneering Chinese American actress Anna May Wong, a trailblazing early Hollywood star and fashion icon.
  • 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: [Frozen Ever After, featuresCharacter, Anna]
Generated description
Anna is a main protagonist from Disney's Frozen franchise, known as the optimistic and fearless princess of Arendelle and sister of Queen Elsa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Anna
Target entity description: Anna is a main protagonist from Disney's Frozen franchise, known as the optimistic and fearless princess of Arendelle and sister of Queen Elsa.
  • A. Anna chosen
    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.
  • B. Anna
    Anna is the given first name of Eleanor Roosevelt, the influential former First Lady of the United States and human rights advocate.
  • C. 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.
  • D. Anna
    Anna was Empress of Russia from 1730 to 1740, known for her autocratic rule and the dominance of her German favorites at court.
  • E. Anna
    Anna is a character from the video game "Surfacing," likely serving as a key figure in the game's narrative or player interactions.
  • F. None of above.

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_69a8891869c88190a02643e3bb746f59 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abba5097ac8190a723a8af2982238c completed March 7, 2026, 5:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef07c3420819097a153052feb1a15 completed March 9, 2026, 4:08 p.m.
NEDg Description generation batch_69aef6548458819090d60af7ea747ae6 completed March 9, 2026, 4:33 p.m.
NED2 Entity disambiguation (via description) batch_69aef76715588190b7e66429f049c4a3 completed March 9, 2026, 4:37 p.m.
Created at: March 4, 2026, 7:41 p.m.