Triple

T3239528
Position Surface form Disambiguated ID Type / Status
Subject Coming to America E67933 entity
Predicate character P662 FINISHED
Object Semmi
Semmi is a comedic supporting character in the film "Coming to America," serving as Prince Akeem's pampered and often reluctant companion from Zamunda.
 E341024 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: Semmi | Statement: [Coming to America, character, Semmi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Semmi
Context triple: [Coming to America, character, Semmi]
  • A. Emme
    Emme is a river in Switzerland that flows through the canton of Bern and is a tributary of the Aare.
  • B. Jotijota
    Jotijota is an alternative name for the Yorta Yorta, an Aboriginal Australian people traditionally from the Murray–Goulburn region of northern Victoria and southern New South Wales.
  • C. Nellallitea
    Nellallitea is the birth name of Nella Larsen, the influential Harlem Renaissance novelist and short story writer known for exploring race and identity.
  • D. Semnoz
    Semnoz is a mountain in the French Alps known for its panoramic views over Lake Annecy and its popular hiking, skiing, and cycling routes.
  • E. Nil Sine Numine
    Nil Sine Numine is a Latin phrase meaning "Nothing without divine will" or "Nothing without the deity," expressing reliance on a higher power.
  • 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: Semmi
Triple: [Coming to America, character, Semmi]
Generated description
Semmi is a comedic supporting character in the film "Coming to America," serving as Prince Akeem's pampered and often reluctant companion from Zamunda.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Semmi
Target entity description: Semmi is a comedic supporting character in the film "Coming to America," serving as Prince Akeem's pampered and often reluctant companion from Zamunda.
  • A. Emme
    Emme is a river in Switzerland that flows through the canton of Bern and is a tributary of the Aare.
  • B. Jotijota
    Jotijota is an alternative name for the Yorta Yorta, an Aboriginal Australian people traditionally from the Murray–Goulburn region of northern Victoria and southern New South Wales.
  • C. Nellallitea
    Nellallitea is the birth name of Nella Larsen, the influential Harlem Renaissance novelist and short story writer known for exploring race and identity.
  • D. Semnoz
    Semnoz is a mountain in the French Alps known for its panoramic views over Lake Annecy and its popular hiking, skiing, and cycling routes.
  • E. Nil Sine Numine
    Nil Sine Numine is a Latin phrase meaning "Nothing without divine will" or "Nothing without the deity," expressing reliance on a higher power.
  • 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_69ad858d27348190abb61c280b4c86a9 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaef4c0bc819095e4f84296fe7cb6 completed March 8, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2774f93448190b8493b457636ae48 completed March 12, 2026, 8:20 a.m.
NEDg Description generation batch_69b2786b7d388190ad0d97bd41a60543 completed March 12, 2026, 8:25 a.m.
NED2 Entity disambiguation (via description) batch_69b27c45f6b08190966fbc3fd28664ec completed March 12, 2026, 8:41 a.m.
Created at: March 8, 2026, 3:08 p.m.