Triple

T12686134
Position Surface form Disambiguated ID Type / Status
Subject Polisse E303071 entity
Predicate starring P1507 FINISHED
Object Karin Viard
Karin Viard is an acclaimed French actress known for her versatile performances in both dramatic and comedic roles in contemporary French cinema.
E1027233 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: Karin Viard | Statement: [Polisse, starring, Karin Viard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karin Viard
Context triple: [Polisse, starring, Karin Viard]
  • A. Nathalie Cresson
    Nathalie Cresson is the daughter of Édith Cresson, the former Prime Minister of France.
  • B. Françoise Castro
    Françoise Castro is a French journalist and writer best known as the wife of prominent Socialist politician and former Prime Minister Laurent Fabius.
  • C. Valérie Rojan
    Valérie Rojan is known as the partner of French film director Philippe de Broca.
  • D. Valérie Létard
    Valérie Létard is a French centrist politician who has served in various governmental and parliamentary roles, notably in social and environmental policy.
  • E. Delphine Delaporte
    Delphine Delaporte is known as the spouse of French business executive Thierry Delaporte, the CEO of Wipro.
  • 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: Karin Viard
Triple: [Polisse, starring, Karin Viard]
Generated description
Karin Viard is an acclaimed French actress known for her versatile performances in both dramatic and comedic roles in contemporary French cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karin Viard
Target entity description: Karin Viard is an acclaimed French actress known for her versatile performances in both dramatic and comedic roles in contemporary French cinema.
  • A. Nathalie Cresson
    Nathalie Cresson is the daughter of Édith Cresson, the former Prime Minister of France.
  • B. Françoise Castro
    Françoise Castro is a French journalist and writer best known as the wife of prominent Socialist politician and former Prime Minister Laurent Fabius.
  • C. Valérie Rojan
    Valérie Rojan is known as the partner of French film director Philippe de Broca.
  • D. Valérie Létard
    Valérie Létard is a French centrist politician who has served in various governmental and parliamentary roles, notably in social and environmental policy.
  • E. Delphine Delaporte
    Delphine Delaporte is known as the spouse of French business executive Thierry Delaporte, the CEO of Wipro.
  • 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_69d7bdee64a08190801c6d470aefd723 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961d7cd4c81909521839ef5859799 completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5b9e0c4819095194dc42677e17f completed May 3, 2026, 7:14 a.m.
NEDg Description generation batch_69f6f80b420c8190b5028be4fa99fb59 completed May 3, 2026, 7:23 a.m.
NED2 Entity disambiguation (via description) batch_69f6f89072a88190b3182f581b1b6762 completed May 3, 2026, 7:26 a.m.
Created at: April 9, 2026, 5:21 p.m.