Triple

T10367485
Position Surface form Disambiguated ID Type / Status
Subject Heartbreaker E244292 entity
Predicate screenwriter P2831 FINISHED
Object Yohann Gromb
Yohann Gromb is a French screenwriter known for his work on the film "Heartbreaker" and other contemporary French comedies.
E863634 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: Yohann Gromb | Statement: [Heartbreaker, screenwriter, Yohann Gromb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yohann Gromb
Context triple: [Heartbreaker, screenwriter, Yohann Gromb]
  • A. Julien Barbagallo
    Julien Barbagallo is a French drummer and musician best known for performing as the live drummer for the psychedelic music project Tame Impala.
  • B. Arnaud Decagny
    Arnaud Decagny is a French local politician who serves as the mayor of the northern town of Maubeuge.
  • C. Matthieu Rougé
    Matthieu Rougé is a French Roman Catholic prelate who serves as the bishop of the Diocese of Nanterre.
  • D. Julien Bertheau
    Julien Bertheau was a French actor known for his work in both classical theatre, particularly with the Comédie-Française, and in notable films by directors such as Luis Buñuel.
  • E. Benoît Lutgen
    Benoît Lutgen is a Belgian politician who has led the francophone centrist party cdH (Centre démocrate humaniste) and held various regional and national political roles.
  • 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: Yohann Gromb
Triple: [Heartbreaker, screenwriter, Yohann Gromb]
Generated description
Yohann Gromb is a French screenwriter known for his work on the film "Heartbreaker" and other contemporary French comedies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yohann Gromb
Target entity description: Yohann Gromb is a French screenwriter known for his work on the film "Heartbreaker" and other contemporary French comedies.
  • A. Julien Barbagallo
    Julien Barbagallo is a French drummer and musician best known for performing as the live drummer for the psychedelic music project Tame Impala.
  • B. Arnaud Decagny
    Arnaud Decagny is a French local politician who serves as the mayor of the northern town of Maubeuge.
  • C. Matthieu Rougé
    Matthieu Rougé is a French Roman Catholic prelate who serves as the bishop of the Diocese of Nanterre.
  • D. Julien Bertheau
    Julien Bertheau was a French actor known for his work in both classical theatre, particularly with the Comédie-Française, and in notable films by directors such as Luis Buñuel.
  • E. Benoît Lutgen
    Benoît Lutgen is a Belgian politician who has led the francophone centrist party cdH (Centre démocrate humaniste) and held various regional and national political roles.
  • 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_69d381b3e328819094b23b8edcd29b5a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e96fd6f081908f630a16106996d9 completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87e64109881908c42a4fbcfd057be completed April 10, 2026, 4:36 a.m.
NEDg Description generation batch_69d886c325c4819089dac35eb26e7961 completed April 10, 2026, 5:12 a.m.
NED2 Entity disambiguation (via description) batch_69d88dbbe97c8190861e08f3ff39f91b completed April 10, 2026, 5:42 a.m.
Created at: April 6, 2026, noon