Triple

T20580420
Position Surface form Disambiguated ID Type / Status
Subject Doña Bárbara E505636 entity
Predicate featuresCharacter P626 FINISHED
Object Marisela
Marisela is a central character in the Venezuelan novel "Doña Bárbara," often portrayed as the innocent and virtuous counterpart to the ruthless title character.
 E1439213 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: Marisela | Statement: [Doña Bárbara, featuresCharacter, Marisela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marisela
Context triple: [Doña Bárbara, featuresCharacter, Marisela]
  • A. Fabiola
    Fabiola is a given name of Latin origin, historically associated with saints and European royalty.
  • B. Ximena
    Ximena is a feminine given name of Spanish origin commonly used in Spanish-speaking countries.
  • C. Marisabel
    Marisabel is a feminine given name of Spanish origin, commonly used in Spanish-speaking countries.
  • D. Yalitza
    Yalitza is a feminine given name most widely recognized through Mexican actress Yalitza Aparicio, who gained international fame for her role in the film "Roma."
  • E. Sheyla
    Sheyla is a feminine given name, typically considered a variant of Sheila or Shayla and used in various cultures.
  • 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: Marisela
Triple: [Doña Bárbara, featuresCharacter, Marisela]
Generated description
Marisela is a central character in the Venezuelan novel "Doña Bárbara," often portrayed as the innocent and virtuous counterpart to the ruthless title character.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marisela
Target entity description: Marisela is a central character in the Venezuelan novel "Doña Bárbara," often portrayed as the innocent and virtuous counterpart to the ruthless title character.
  • A. Fabiola
    Fabiola is a given name of Latin origin, historically associated with saints and European royalty.
  • B. Ximena
    Ximena is a feminine given name of Spanish origin commonly used in Spanish-speaking countries.
  • C. Marisabel
    Marisabel is a feminine given name of Spanish origin, commonly used in Spanish-speaking countries.
  • D. Yalitza
    Yalitza is a feminine given name most widely recognized through Mexican actress Yalitza Aparicio, who gained international fame for her role in the film "Roma."
  • E. Sheyla
    Sheyla is a feminine given name, typically considered a variant of Sheila or Shayla and used in various cultures.
  • 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_69e0b4b9669c8190b8e81fc72817d42c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a90dd3e881908915debe1f1e8509 completed April 20, 2026, 10:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08aceaa8dc819094d7ba5e7aa0d24e completed May 16, 2026, 5:44 p.m.
NEDg Description generation batch_6a08b0b7e9908190866a9929f88c2b2b completed May 16, 2026, 6 p.m.
NED2 Entity disambiguation (via description) batch_6a08b18f6ab08190a726e7cca7b8787f completed May 16, 2026, 6:03 p.m.
Created at: April 16, 2026, 11:39 a.m.