Triple

T984995
Position Surface form Disambiguated ID Type / Status
Subject Only Lovers Left Alive E21258 entity
Predicate screenwriter P2831 FINISHED
Object Marion Bessay
Marion Bessay is a screenwriter known for her work on the film "Only Lovers Left Alive."
E144484 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: Marion Bessay | Statement: [Only Lovers Left Alive, screenwriter, Marion Bessay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Bessay
Context triple: [Only Lovers Left Alive, screenwriter, Marion Bessay]
  • A. Marie De Forest
    Marie De Forest, better known as Marie Mosquini, was an American silent film actress who frequently appeared in Hal Roach comedies during the 1910s and 1920s.
  • B. Lucile Rosson
    Lucile Rosson was the wife of American film director Victor Fleming, known for his work during Hollywood’s Golden Age.
  • C. Blanche Coudert
    Blanche Coudert was the wife of American cinematographer Arthur C. Miller, known for her connection to his life and career in early Hollywood.
  • D. Anne Bauchens
    Anne Bauchens was an American film editor best known for her long collaboration with director Cecil B. DeMille and for being one of the first women to win an Academy Award for film editing.
  • E. Marie Lamfrom
    Marie Lamfrom was a German-born businesswoman and Holocaust refugee who co-founded Columbia Sportswear and helped build it into a major outdoor apparel company.
  • 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: Marion Bessay
Triple: [Only Lovers Left Alive, screenwriter, Marion Bessay]
Generated description
Marion Bessay is a screenwriter known for her work on the film "Only Lovers Left Alive."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marion Bessay
Target entity description: Marion Bessay is a screenwriter known for her work on the film "Only Lovers Left Alive."
  • A. Marie De Forest
    Marie De Forest, better known as Marie Mosquini, was an American silent film actress who frequently appeared in Hal Roach comedies during the 1910s and 1920s.
  • B. Lucile Rosson
    Lucile Rosson was the wife of American film director Victor Fleming, known for his work during Hollywood’s Golden Age.
  • C. Blanche Coudert
    Blanche Coudert was the wife of American cinematographer Arthur C. Miller, known for her connection to his life and career in early Hollywood.
  • D. Anne Bauchens
    Anne Bauchens was an American film editor best known for her long collaboration with director Cecil B. DeMille and for being one of the first women to win an Academy Award for film editing.
  • E. Marie Lamfrom
    Marie Lamfrom was a German-born businesswoman and Holocaust refugee who co-founded Columbia Sportswear and helped build it into a major outdoor apparel company.
  • 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_69a493c383dc8190a03257f22d4b4183 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4959fe48190a78bd811cbc888ab completed March 1, 2026, 9:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac9968ff4c81909e8e454b7e1e9137 completed March 7, 2026, 9:32 p.m.
NEDg Description generation batch_69ac9a04f5f88190922a49ad5c83d794 completed March 7, 2026, 9:35 p.m.
NED2 Entity disambiguation (via description) batch_69ac9a793e7081908374e1a8e9fe3137 completed March 7, 2026, 9:36 p.m.
Created at: March 1, 2026, 7:41 p.m.