Triple

T11203267
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth Swann E265093 entity
Predicate portrayedBy P1507 FINISHED
Object Lucinda Dryzek
Lucinda Dryzek is an English actress best known for her early role as the young Elizabeth Swann in the film "Pirates of the Caribbean: The Curse of the Black Pearl."
 E945143 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: Lucinda Dryzek | Statement: [Elizabeth Swann, portrayedBy, Lucinda Dryzek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lucinda Dryzek
Context triple: [Elizabeth Swann, portrayedBy, Lucinda Dryzek]
  • A. Valerie O'Herlihy
    Valerie O'Herlihy is known as the wife of Irish-born television and film director Michael O'Herlihy.
  • B. Donna Lindsay
    Donna Lindsay was the first wife of American medical researcher Jonas Salk, with whom she shared much of his early career and family life.
  • C. Janine Dunn
    Janine Dunn is the wife of country music singer Ronnie Dunn, known for her long-term marriage and support of his career.
  • D. Linda Gunderson
    Linda Gunderson is a kind-hearted Minnesota bookshop owner who becomes the human protagonist and caretaker of the rare macaw Blu in the animated film "Rio."
  • E. Janine Melnitz
    Janine Melnitz is the Ghostbusters’ sharp-tongued, no-nonsense receptionist who provides comic relief and grounded support to the team.
  • 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: Lucinda Dryzek
Triple: [Elizabeth Swann, portrayedBy, Lucinda Dryzek]
Generated description
Lucinda Dryzek is an English actress best known for her early role as the young Elizabeth Swann in the film "Pirates of the Caribbean: The Curse of the Black Pearl."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lucinda Dryzek
Target entity description: Lucinda Dryzek is an English actress best known for her early role as the young Elizabeth Swann in the film "Pirates of the Caribbean: The Curse of the Black Pearl."
  • A. Valerie O'Herlihy
    Valerie O'Herlihy is known as the wife of Irish-born television and film director Michael O'Herlihy.
  • B. Donna Lindsay
    Donna Lindsay was the first wife of American medical researcher Jonas Salk, with whom she shared much of his early career and family life.
  • C. Janine Dunn
    Janine Dunn is the wife of country music singer Ronnie Dunn, known for her long-term marriage and support of his career.
  • D. Linda Gunderson
    Linda Gunderson is a kind-hearted Minnesota bookshop owner who becomes the human protagonist and caretaker of the rare macaw Blu in the animated film "Rio."
  • E. Janine Melnitz
    Janine Melnitz is the Ghostbusters’ sharp-tongued, no-nonsense receptionist who provides comic relief and grounded support to the team.
  • 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_69d6aa9eb9248190b20211772621b4bc completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8d355c481908fc3d555b596314d completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69f08f0d9d0c8190a7b84e647c7491e9 completed April 28, 2026, 10:42 a.m.
NEDg Description generation batch_69f0bd36673881908530b68e496c3d2e completed April 28, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69f0eec1f5d081908624fe2a93995fe5 completed April 28, 2026, 5:30 p.m.
Created at: April 8, 2026, 9:29 p.m.