Triple

T7560424
Position Surface form Disambiguated ID Type / Status
Subject Castle E178779 entity
Predicate starring P1507 FINISHED
Object Susan Sullivan
Susan Sullivan is an American actress best known for her television roles in series such as "Falcon Crest," "Dharma & Greg," and "Castle."
E705777 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: Susan Sullivan | Statement: [Castle, starring, Susan Sullivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Sullivan
Context triple: [Castle, starring, Susan Sullivan]
  • A. Tricia Sullivan
    Tricia Sullivan is an American-born science fiction author known for her innovative, genre-bending novels and award-winning contributions to speculative fiction.
  • B. Nancy Sullivan
    Nancy Sullivan is an actress known for playing Éponine in stage productions of the musical "Les Misérables."
  • C. Shirley Sullivan
    Shirley Sullivan is best known as the mother of American actor Cuba Gooding Jr.
  • D. Kayte Walsh
    Kayte Walsh is a British former flight attendant who is best known as the wife of American actor Kelsey Grammer.
  • E. Mary Beth Hughes
    Mary Beth Hughes was an American film and television actress best known for her roles in 1940s Hollywood dramas and crime films.
  • 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: Susan Sullivan
Triple: [Castle, starring, Susan Sullivan]
Generated description
Susan Sullivan is an American actress best known for her television roles in series such as "Falcon Crest," "Dharma & Greg," and "Castle."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Susan Sullivan
Target entity description: Susan Sullivan is an American actress best known for her television roles in series such as "Falcon Crest," "Dharma & Greg," and "Castle."
  • A. Tricia Sullivan
    Tricia Sullivan is an American-born science fiction author known for her innovative, genre-bending novels and award-winning contributions to speculative fiction.
  • B. Nancy Sullivan
    Nancy Sullivan is an actress known for playing Éponine in stage productions of the musical "Les Misérables."
  • C. Shirley Sullivan
    Shirley Sullivan is best known as the mother of American actor Cuba Gooding Jr.
  • D. Kayte Walsh
    Kayte Walsh is a British former flight attendant who is best known as the wife of American actor Kelsey Grammer.
  • E. Mary Beth Hughes
    Mary Beth Hughes was an American film and television actress best known for her roles in 1940s Hollywood dramas and crime films.
  • 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_69c69f2f80288190b95cceb4da92ab2b completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f8dd96488190b4cca25ae8f7f95c completed March 27, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69cc55bdf8c0819083b61987d70f21ca completed March 31, 2026, 11:16 p.m.
NEDg Description generation batch_69cc5822581481908a143376bee599ec completed March 31, 2026, 11:26 p.m.
NED2 Entity disambiguation (via description) batch_69cc58f549388190ba6c8b41c0820cd6 completed March 31, 2026, 11:29 p.m.
Created at: March 27, 2026, 3:50 p.m.