Triple

T21018201
Position Surface form Disambiguated ID Type / Status
Subject Niki Karimi E517734 entity
Predicate notableWork P4 FINISHED
Object Sara
Sara is a critically acclaimed Iranian film directed by Niki Karimi, known for its nuanced portrayal of a woman's struggles within a traditional society.
E1462879 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: Sara | Statement: [Niki Karimi, notableWork, Sara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara
Context triple: [Niki Karimi, notableWork, Sara]
  • A. Sara
    "Sara" is a soft rock song by Fleetwood Mac, written and sung by Stevie Nicks, known for its dreamy lyrics and prominent place on their 1979 album *Tusk*.
  • B. Sara
    Sara is the imaginative and resilient young heroine of Frances Hodgson Burnett’s classic children’s novel "A Little Princess."
  • C. Sara
    Sara is the central protagonist of the film "Runaway Train," around whom the story’s dramatic events and emotional stakes revolve.
  • D. Sara
    Sara is the central female protagonist of the Italian film "L’uomo che ama," around whom the story’s emotional and relational conflicts revolve.
  • E. Sara
    Sara is the first name of Sara Blakely, the American entrepreneur and founder of the shapewear company Spanx.
  • 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: Sara
Triple: [Niki Karimi, notableWork, Sara]
Generated description
Sara is a critically acclaimed Iranian film directed by Niki Karimi, known for its nuanced portrayal of a woman's struggles within a traditional society.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sara
Target entity description: Sara is a critically acclaimed Iranian film directed by Niki Karimi, known for its nuanced portrayal of a woman's struggles within a traditional society.
  • A. Sara
    Sara is the central female protagonist of the Italian film "L’uomo che ama," around whom the story’s emotional and relational conflicts revolve.
  • B. Sara
    Sara is the given name of the Irish stage and film actress Sara Allgood, known for her work in early 20th-century theatre and cinema.
  • C. Sara
    Sara is the central protagonist of the film "Runaway Train," around whom the story’s dramatic events and emotional stakes revolve.
  • D. Sara
    "Sara" is a 1997 Polish drama film directed by Maciej Ślesicki, starring Bogusław Linda as a bodyguard protecting a teenage girl, and is one of his best-known screen roles.
  • E. Sara
    Sara is a skilled warrior and love interest of the Huntsman in the fantasy film "The Huntsman: Winter’s War."
  • 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_69e0b50262b081909bc488937145eb73 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc5a27f08190b26828a6a7b59f7c completed April 21, 2026, 4:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b67103081908033c57e586afa69 completed May 17, 2026, 3:52 a.m.
NEDg Description generation batch_6a0940b362388190a78a244eafa7cbba completed May 17, 2026, 4:14 a.m.
NED2 Entity disambiguation (via description) batch_6a09414912d88190b7da0186ef7b227f completed May 17, 2026, 4:17 a.m.
Created at: April 16, 2026, 1:54 p.m.