Triple

T12242898
Position Surface form Disambiguated ID Type / Status
Subject La rondine E291778 entity
Predicate mainCharacter P1183 FINISHED
Object Lisette
Lisette is a character in Giacomo Puccini's opera "La rondine," serving as the maid and comic counterpart to the heroine, Magda.
E980760 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: Lisette | Statement: [La rondine, mainCharacter, Lisette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisette
Context triple: [La rondine, mainCharacter, Lisette]
  • A. Lizette
    Lizette is the nickname of American actress Elizabeth Rooney Mara, known for her roles in films like "The Girl with the Dragon Tattoo" and "Carol."
  • B. Rosita
    Rosita is a shy but talented pig and devoted mother who becomes a standout performer in the animated musical film "Sing."
  • C. Rosita
    Rosita is a bilingual, turquoise monster Muppet on Sesame Street known for introducing Spanish language and Latino culture to the show.
  • D. Lillita
    Lillita is the birth name of Lita Grey, the American actress best known for her early silent film work and marriage to Charlie Chaplin.
  • E. Luisa
    Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
  • 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: Lisette
Triple: [La rondine, mainCharacter, Lisette]
Generated description
Lisette is a character in Giacomo Puccini's opera "La rondine," serving as the maid and comic counterpart to the heroine, Magda.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lisette
Target entity description: Lisette is a character in Giacomo Puccini's opera "La rondine," serving as the maid and comic counterpart to the heroine, Magda.
  • A. Lizette
    Lizette is the nickname of American actress Elizabeth Rooney Mara, known for her roles in films like "The Girl with the Dragon Tattoo" and "Carol."
  • B. Rosita
    Rosita is a shy but talented pig and devoted mother who becomes a standout performer in the animated musical film "Sing."
  • C. Rosita
    Rosita is a bilingual, turquoise monster Muppet on Sesame Street known for introducing Spanish language and Latino culture to the show.
  • D. Lillita
    Lillita is the birth name of Lita Grey, the American actress best known for her early silent film work and marriage to Charlie Chaplin.
  • E. Luisa
    Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
  • 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_69d6ab67950c8190be08450a06228c4b completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cb724448190be29fc1d2b946ab7 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6346016848190ba864a3d46280c5a completed May 2, 2026, 5:29 p.m.
NEDg Description generation batch_69f635f094e48190be7d86d1236058dc completed May 2, 2026, 5:35 p.m.
NED2 Entity disambiguation (via description) batch_69f636d727a08190882eec3fd664b64d completed May 2, 2026, 5:39 p.m.
Created at: April 8, 2026, 9:51 p.m.