Triple

T9565703
Position Surface form Disambiguated ID Type / Status
Subject Sophie Sheridan E230782 entity
Predicate closeFriend P8712 FINISHED
Object Lisa
Lisa is a close friend and confidante of Sophie Sheridan in the Mamma Mia! universe.
 E807916 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: Lisa | Statement: [Sophie Sheridan, closeFriend, Lisa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lisa
Context triple: [Sophie Sheridan, closeFriend, Lisa]
  • A. Lisa
    Lisa is a central character in the science fiction adventure film "Zathura: A Space Adventure," where she becomes unwittingly involved in her younger brothers' perilous journey through outer space.
  • B. Lisa
    Lisa is a feminine given name commonly used in English-speaking countries, often as a shortened form of Elizabeth or Melissa.
  • C. Lisa
    Lisa is the central female protagonist of the film "The Other Man," around whom the story’s romantic and dramatic tensions revolve.
  • D. Lisa
    Lisa is a fictional character from the psychological horror film "The Voices," known for her involvement with the disturbed protagonist and the film’s darkly comedic, violent events.
  • E. Lisa
    Lisa is a custom-designed integrated circuit that served as a key support chipset component in early Apple Macintosh computers, handling functions such as memory and system control.
  • 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: Lisa
Triple: [Sophie Sheridan, closeFriend, Lisa]
Generated description
Lisa is a close friend and confidante of Sophie Sheridan in the Mamma Mia! universe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lisa
Target entity description: Lisa is a close friend and confidante of Sophie Sheridan in the Mamma Mia! universe.
  • A. Lisa
    Lisa is the central protagonist of the film "Wicker Park," around whom the story’s romantic mystery and emotional tension revolve.
  • B. Lisa
    Lisa is the central female protagonist of the film "The Other Man," around whom the story’s romantic and dramatic tensions revolve.
  • C. Lisa
    Lisa is a fictional character from the psychological horror film "The Voices," known for her involvement with the disturbed protagonist and the film’s darkly comedic, violent events.
  • D. Lisa
    Lisa is a person known primarily for holding a position or role that was later taken over by Denise.
  • E. Lisa
    Lisa is a feminine given name commonly used in English-speaking countries, often as a shortened form of Elizabeth or Melissa.
  • 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_69ca847f22188190a56e4a97625bef22 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd996c0a1081908a8356c454e60f74 completed April 1, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69d152abb0788190ab2e204d9a082ccf completed April 4, 2026, 6:04 p.m.
NEDg Description generation batch_69d15565623c81908112183b65464553 completed April 4, 2026, 6:16 p.m.
NED2 Entity disambiguation (via description) batch_69d1560bbe3481908c98d74d21b33e63 completed April 4, 2026, 6:18 p.m.
Created at: March 30, 2026, 8:04 p.m.