Triple

T20996978
Position Surface form Disambiguated ID Type / Status
Subject Fanny and Alexander E517173 entity
Predicate hasCharacter P2308 FINISHED
Object Fanny Ekdahl
Fanny Ekdahl is one of the central child protagonists in Ingmar Bergman’s film and television series "Fanny and Alexander," representing innocence and family bonds amid the story’s dramatic and supernatural events.
E1472315 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: Fanny Ekdahl | Statement: [Fanny and Alexander, hasCharacter, Fanny Ekdahl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fanny Ekdahl
Context triple: [Fanny and Alexander, hasCharacter, Fanny Ekdahl]
  • A. Fanny Lönnbohm
    Fanny Lönnbohm was the wife of renowned Finnish poet and journalist Eino Leino.
  • B. Helena Almqvist
    Helena Almqvist is a person notable for bearing the Swedish surname Almqvist.
  • C. Anna Matilda Forsman
    Anna Matilda Forsman was the first wife of Finnish statesman and later President Juho Kusti Paasikivi.
  • D. Elvera Stromberg
    Elvera Stromberg was the wife of Warren E. Burger, the 15th Chief Justice of the United States.
  • E. Maud Olofsson
    Maud Olofsson is a Swedish politician who served as leader of the Centre Party and as Deputy Prime Minister of Sweden in the 2000s.
  • 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: Fanny Ekdahl
Triple: [Fanny and Alexander, hasCharacter, Fanny Ekdahl]
Generated description
Fanny Ekdahl is one of the central child protagonists in Ingmar Bergman’s film and television series "Fanny and Alexander," representing innocence and family bonds amid the story’s dramatic and supernatural events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fanny Ekdahl
Target entity description: Fanny Ekdahl is one of the central child protagonists in Ingmar Bergman’s film and television series "Fanny and Alexander," representing innocence and family bonds amid the story’s dramatic and supernatural events.
  • A. Fanny Lönnbohm
    Fanny Lönnbohm was the wife of renowned Finnish poet and journalist Eino Leino.
  • B. Helena Almqvist
    Helena Almqvist is a person notable for bearing the Swedish surname Almqvist.
  • C. Anna Matilda Forsman
    Anna Matilda Forsman was the first wife of Finnish statesman and later President Juho Kusti Paasikivi.
  • D. Elvera Stromberg
    Elvera Stromberg was the wife of Warren E. Burger, the 15th Chief Justice of the United States.
  • E. Maud Olofsson
    Maud Olofsson is a Swedish politician who served as leader of the Centre Party and as Deputy Prime Minister of Sweden in the 2000s.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc21838081909872eed21bc12a08 completed April 21, 2026, 4:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a097eb77c748190a87f51754a93448b completed May 17, 2026, 8:39 a.m.
NEDg Description generation batch_6a098258757c8190b394f20074093f58 completed May 17, 2026, 8:54 a.m.
NED2 Entity disambiguation (via description) batch_6a0982a8fc7c81909c47076b33bcb24a completed May 17, 2026, 8:56 a.m.
Created at: April 16, 2026, 1:51 p.m.