Triple

T9762308
Position Surface form Disambiguated ID Type / Status
Subject Mamá Coco E236698 entity
Predicate nameInEnglish P3437 FINISHED
Object Mama Coco
Mama Coco is a central elderly character in Pixar’s animated film "Coco," known as Miguel’s great-grandmother whose memories are key to preserving her father’s legacy.
E820460 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: Mama Coco | Statement: [Mamá Coco, nameInEnglish, Mama Coco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mama Coco
Context triple: [Mamá Coco, nameInEnglish, Mama Coco]
  • A. Lolita Baucaire
    Lolita Baucaire was the first wife of American writer and self-improvement pioneer Dale Carnegie.
  • B. Baba Marta
    Baba Marta is a traditional Bulgarian holiday on March 1st that welcomes the coming of spring, marked by the exchange of red-and-white martenitsa adornments for health and good fortune.
  • C. Nené
    Nené is a former Brazilian footballer best known as a prolific forward for S.L. Benfica during the 1970s and 1980s.
  • D. Miqui
    Miqui is a diminutive or affectionate short form of the given name Miquel, commonly used in Catalan- and Spanish-speaking contexts.
  • E. Irma Santos
    Irma Santos is best known as the wife of influential Cuban-American businessman and anti-Castro activist Jorge Mas Canosa.
  • 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: Mama Coco
Triple: [Mamá Coco, nameInEnglish, Mama Coco]
Generated description
Mama Coco is a central elderly character in Pixar’s animated film "Coco," known as Miguel’s great-grandmother whose memories are key to preserving her father’s legacy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mama Coco
Target entity description: Mama Coco is a central elderly character in Pixar’s animated film "Coco," known as Miguel’s great-grandmother whose memories are key to preserving her father’s legacy.
  • A. Lolita Baucaire
    Lolita Baucaire was the first wife of American writer and self-improvement pioneer Dale Carnegie.
  • B. Baba Marta
    Baba Marta is a traditional Bulgarian holiday on March 1st that welcomes the coming of spring, marked by the exchange of red-and-white martenitsa adornments for health and good fortune.
  • C. Nené
    Nené is a former Brazilian footballer best known as a prolific forward for S.L. Benfica during the 1970s and 1980s.
  • D. Miqui
    Miqui is a diminutive or affectionate short form of the given name Miquel, commonly used in Catalan- and Spanish-speaking contexts.
  • E. Irma Santos
    Irma Santos is best known as the wife of influential Cuban-American businessman and anti-Castro activist Jorge Mas Canosa.
  • 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_69ca84d64f6c8190a4ed4e9f5936eda5 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda04c70108190a8ed09eb6f2a124e completed April 1, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bcec777c81908b2eff64f4756517 completed April 5, 2026, 1:37 a.m.
NEDg Description generation batch_69d1beefbd1c8190bab597373231cca1 completed April 5, 2026, 1:46 a.m.
NED2 Entity disambiguation (via description) batch_69d1bf4bb6088190801095cacd218571 completed April 5, 2026, 1:47 a.m.
Created at: March 30, 2026, 8:25 p.m.