Triple

T8999695
Position Surface form Disambiguated ID Type / Status
Subject Marked Woman E215010 entity
Predicate screenwriter P2831 FINISHED
Object Lorry Knapp
Lorry Knapp is a screenwriter best known for her work on the film "Marked Woman."
E772171 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: Lorry Knapp | Statement: [Marked Woman, screenwriter, Lorry Knapp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lorry Knapp
Context triple: [Marked Woman, screenwriter, Lorry Knapp]
  • A. Lee Marrow
    Lee Marrow is an Italian music producer and DJ best known for his influential work in 1990s Eurodance, including creating the sound behind Corona’s hit "The Rhythm of the Night."
  • B. John Keeble
    John Keeble is an English drummer best known as a founding member of the 1980s new wave band Spandau Ballet.
  • C. Cator Woolford
    Cator Woolford was an American businessman and entrepreneur best known as a co-founder of the credit reporting company that became Equifax.
  • D. Norman Rodway
    Norman Rodway was an Irish actor known for his work in classical theatre and film, particularly in Shakespearean roles and British television dramas.
  • E. Joseph Keeble
    Joseph Keeble is a fictional wealthy, good-natured financier in P. G. Wodehouse’s Blandings Castle stories, known for his indulgent generosity and mild-mannered temperament.
  • 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: Lorry Knapp
Triple: [Marked Woman, screenwriter, Lorry Knapp]
Generated description
Lorry Knapp is a screenwriter best known for her work on the film "Marked Woman."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lorry Knapp
Target entity description: Lorry Knapp is a screenwriter best known for her work on the film "Marked Woman."
  • A. Lee Marrow
    Lee Marrow is an Italian music producer and DJ best known for his influential work in 1990s Eurodance, including creating the sound behind Corona’s hit "The Rhythm of the Night."
  • B. John Keeble
    John Keeble is an English drummer best known as a founding member of the 1980s new wave band Spandau Ballet.
  • C. Cator Woolford
    Cator Woolford was an American businessman and entrepreneur best known as a co-founder of the credit reporting company that became Equifax.
  • D. Norman Rodway
    Norman Rodway was an Irish actor known for his work in classical theatre and film, particularly in Shakespearean roles and British television dramas.
  • E. Joseph Keeble
    Joseph Keeble is a fictional wealthy, good-natured financier in P. G. Wodehouse’s Blandings Castle stories, known for his indulgent generosity and mild-mannered temperament.
  • 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_69ca83a12d648190b1e4fe11e8a31890 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc68e3b1f48190bbeafbce363fff53 completed April 1, 2026, 12:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0d987dc81908f1d74f390f18a9c completed April 3, 2026, 2:38 p.m.
NEDg Description generation batch_69cfd1a32a64819090d423a99ab75362 completed April 3, 2026, 2:41 p.m.
NED2 Entity disambiguation (via description) batch_69cfd250593881908312200ba7bba617 completed April 3, 2026, 2:44 p.m.
Created at: March 30, 2026, 7:05 p.m.