Triple

T856139
Position Surface form Disambiguated ID Type / Status
Subject Billy Wilder E18495 entity
Predicate directed P7373 FINISHED
Object Irma la Douce
Irma la Douce is a 1963 romantic comedy film starring Jack Lemmon and Shirley MacLaine, adapted from the French stage musical of the same name.
 E107741 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: Irma la Douce | Statement: [Billy Wilder, directed, Irma la Douce]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Irma la Douce
Context triple: [Billy Wilder, directed, Irma la Douce]
  • A. Micheline
    Micheline is a feminine given name of French origin, commonly used in French-speaking countries.
  • B. Estelle
    Estelle is a British singer, rapper, and songwriter best known for her hit single "American Boy" featuring Kanye West.
  • C. Clémentine
    Clémentine is a feminine given name of French origin, commonly used in Francophone countries and beyond.
  • D. Louise
    Louise is a feminine given name of French origin, traditionally associated with nobility and widely used in many European and English-speaking countries.
  • E. Marie
    Marie is a widely used European given name, especially common in French-speaking countries, derived from the Hebrew name Miryam (Mary).
  • 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: Irma la Douce
Triple: [Billy Wilder, directed, Irma la Douce]
Generated description
Irma la Douce is a 1963 romantic comedy film starring Jack Lemmon and Shirley MacLaine, adapted from the French stage musical of the same name.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Irma la Douce
Target entity description: Irma la Douce is a 1963 romantic comedy film starring Jack Lemmon and Shirley MacLaine, adapted from the French stage musical of the same name.
  • A. Micheline
    Micheline is a feminine given name of French origin, commonly used in French-speaking countries.
  • B. Estelle
    Estelle is a British singer, rapper, and songwriter best known for her hit single "American Boy" featuring Kanye West.
  • C. Clémentine
    Clémentine is a feminine given name of French origin, commonly used in Francophone countries and beyond.
  • D. Louise
    Louise is a feminine given name of French origin, traditionally associated with nobility and widely used in many European and English-speaking countries.
  • E. Marie
    Marie is a widely used European given name, especially common in French-speaking countries, derived from the Hebrew name Miryam (Mary).
  • 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_69a4938bdd3c8190a954a3c11844d9cf completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac3c172481908ed164ee1579ec28 completed March 1, 2026, 9:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7cf53ee748190b5a08bd7a6d0614c completed March 4, 2026, 6:21 a.m.
NEDg Description generation batch_69a7cfbf8cf08190b41d4e322e1bc61c completed March 4, 2026, 6:22 a.m.
NED2 Entity disambiguation (via description) batch_69a7d01bd97081909d176e8fbb096859 completed March 4, 2026, 6:24 a.m.
Created at: March 1, 2026, 7:39 p.m.