Triple

T13779906
Position Surface form Disambiguated ID Type / Status
Subject Total Divas E331105 entity
Predicate features P997 FINISHED
Object Carmella
Carmella is an American professional wrestler and television personality best known for her work with WWE and appearances on the reality series Total Divas.
E1060853 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: Carmella | Statement: [Total Divas, features, Carmella]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carmella
Context triple: [Total Divas, features, Carmella]
  • A. Carmella DeCesare
    Carmella DeCesare is an American model and former Playboy Playmate who gained prominence as Playboy's Playmate of the Year in 2004.
  • B. Adrienne Lubeau
    Adrienne Lubeau is known as the former wife of influential American street photographer Garry Winogrand.
  • C. Carmela
    Carmela is a feminine given name of Latin origin, commonly used in Spanish- and Italian-speaking countries and often associated with religious and cultural traditions.
  • D. Adrienne
    Adrienne is a feminine given name of French origin, commonly used in English- and French-speaking countries.
  • E. Drisella
    Drisella is one of Cinderella’s vain and spiteful stepsisters in Disney’s 2015 live-action adaptation of the classic fairy tale.
  • 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: Carmella
Triple: [Total Divas, features, Carmella]
Generated description
Carmella is an American professional wrestler and television personality best known for her work with WWE and appearances on the reality series Total Divas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carmella
Target entity description: Carmella is an American professional wrestler and television personality best known for her work with WWE and appearances on the reality series Total Divas.
  • A. Carmella DeCesare
    Carmella DeCesare is an American model and former Playboy Playmate who gained prominence as Playboy's Playmate of the Year in 2004.
  • B. Adrienne Lubeau
    Adrienne Lubeau is known as the former wife of influential American street photographer Garry Winogrand.
  • C. Carmela
    Carmela is a feminine given name of Latin origin, commonly used in Spanish- and Italian-speaking countries and often associated with religious and cultural traditions.
  • D. Adrienne
    Adrienne is a feminine given name of French origin, commonly used in English- and French-speaking countries.
  • E. Drisella
    Drisella is one of Cinderella’s vain and spiteful stepsisters in Disney’s 2015 live-action adaptation of the classic fairy tale.
  • 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02460a688190a27874f8d35819c7 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b07670b08190a205d3c7ccb9dded completed May 3, 2026, 8:30 p.m.
NEDg Description generation batch_69f7b0f912f081908084042860c922cb completed May 3, 2026, 8:32 p.m.
NED2 Entity disambiguation (via description) batch_69f7b16a43188190968d5cdf32e447ec completed May 3, 2026, 8:34 p.m.
Created at: April 9, 2026, 10:11 p.m.