Triple

T17340311
Position Surface form Disambiguated ID Type / Status
Subject Stolen Kisses E421048 entity
Predicate cinematographyBy P1953 FINISHED
Object Denis Clair
Denis Clair was a French cinematographer known for his work on François Truffaut’s film "Stolen Kisses."
E1262377 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: Denis Clair | Statement: [Stolen Kisses, cinematographyBy, Denis Clair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Denis Clair
Context triple: [Stolen Kisses, cinematographyBy, Denis Clair]
  • A. Douglas Gerrard
    Douglas Gerrard was an early 20th-century film actor and director who appeared in numerous silent-era productions.
  • B. Michael Aldrich
    Michael Aldrich was a British inventor and entrepreneur best known for pioneering online shopping and developing one of the first systems to connect consumers to businesses via a domestic television and telephone line.
  • C. Hal Gibney
    Hal Gibney was an American radio and television announcer best known for his work on the crime drama series "Dragnet."
  • D. Lee Thompson
    Lee Thompson is a British saxophonist and songwriter best known as a founding member of the ska band Madness.
  • E. Justin Moorhouse
    Justin Moorhouse is an English stand-up comedian and actor best known for his work on the sitcom "Phoenix Nights" and his appearances on British radio and television comedy shows.
  • 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: Denis Clair
Triple: [Stolen Kisses, cinematographyBy, Denis Clair]
Generated description
Denis Clair was a French cinematographer known for his work on François Truffaut’s film "Stolen Kisses."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Denis Clair
Target entity description: Denis Clair was a French cinematographer known for his work on François Truffaut’s film "Stolen Kisses."
  • A. Douglas Gerrard
    Douglas Gerrard was an early 20th-century film actor and director who appeared in numerous silent-era productions.
  • B. Michael Aldrich
    Michael Aldrich was a British inventor and entrepreneur best known for pioneering online shopping and developing one of the first systems to connect consumers to businesses via a domestic television and telephone line.
  • C. Hal Gibney
    Hal Gibney was an American radio and television announcer best known for his work on the crime drama series "Dragnet."
  • D. Lee Thompson
    Lee Thompson is a British saxophonist and songwriter best known as a founding member of the ska band Madness.
  • E. Justin Moorhouse
    Justin Moorhouse is an English stand-up comedian and actor best known for his work on the sitcom "Phoenix Nights" and his appearances on British radio and television comedy shows.
  • 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_69d889d3adc881909319f1edb8d2a956 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a14ec90819098db2ac0d58a53e1 completed April 19, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a018c588a7081909ab108cb4adfedfe completed May 11, 2026, 7:59 a.m.
NEDg Description generation batch_6a018e0f09c881909296656b2732bf1e completed May 11, 2026, 8:06 a.m.
NED2 Entity disambiguation (via description) batch_6a018e7b453c81909f75593237bcf9ec completed May 11, 2026, 8:08 a.m.
Created at: April 10, 2026, 5:44 a.m.