Triple

T14567164
Position Surface form Disambiguated ID Type / Status
Subject Delicatessen E341813 entity
Predicate character P662 FINISHED
Object Clapet
Clapet is the sinister butcher and landlord who serves as the main antagonist in the darkly comic French film "Delicatessen."
 E1106750 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: Clapet | Statement: [Delicatessen, character, Clapet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Clapet
Context triple: [Delicatessen, character, Clapet]
  • A. Clopin
    Clopin is the colorful, charismatic leader of the gypsies and narrator figure in the stage musical adaptation of "The Hunchback of Notre Dame."
  • B. Boite
    The Boite is a mountain river in the Dolomites of northern Italy that flows through the town of Cortina d'Ampezzo before joining the Piave.
  • C. Labouret
    Labouret is a French surname associated with individuals such as Marie-Louise Élisabeth Labouret.
  • D. Chapotel
    Chapotel is a French surname associated with individuals such as Rose Chapotel.
  • E. Drap
    Drap is a small commune in the Alpes-Maritimes department of southeastern France, situated near Nice on the French Riviera.
  • 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: Clapet
Triple: [Delicatessen, character, Clapet]
Generated description
Clapet is the sinister butcher and landlord who serves as the main antagonist in the darkly comic French film "Delicatessen."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Clapet
Target entity description: Clapet is the sinister butcher and landlord who serves as the main antagonist in the darkly comic French film "Delicatessen."
  • A. Clopin
    Clopin is the colorful, charismatic leader of the gypsies and narrator figure in the stage musical adaptation of "The Hunchback of Notre Dame."
  • B. Boite
    The Boite is a mountain river in the Dolomites of northern Italy that flows through the town of Cortina d'Ampezzo before joining the Piave.
  • C. Labouret
    Labouret is a French surname associated with individuals such as Marie-Louise Élisabeth Labouret.
  • D. Chapotel
    Chapotel is a French surname associated with individuals such as Rose Chapotel.
  • E. Drap
    Drap is a small commune in the Alpes-Maritimes department of southeastern France, situated near Nice on the French Riviera.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb38d89fc819086709fd3607b835f completed April 14, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ac669cc819083e05620b1e8c370 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8c5b09448190ad084746a6dd23f5 completed May 8, 2026, 7:10 a.m.
NED2 Entity disambiguation (via description) batch_69fd8d609684819090a9c3f2304f4a6a completed May 8, 2026, 7:14 a.m.
Created at: April 10, 2026, 1:23 a.m.