Triple

T13285853
Position Surface form Disambiguated ID Type / Status
Subject Regis Philbin E316441 entity
Predicate spouse P13 FINISHED
Object Catherine Faylen
Catherine Faylen is an American actress best known for her film and television roles in the 1940s and 1950s.
E1054760 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: Catherine Faylen | Statement: [Regis Philbin, spouse, Catherine Faylen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catherine Faylen
Context triple: [Regis Philbin, spouse, Catherine Faylen]
  • A. Catherine Meyer
    Catherine Meyer is the socially awkward, long-suffering daughter of fictional U.S. Vice President and President Selina Meyer on the television series "Veep."
  • B. Catherine Hickland
    Catherine Hickland is an American actress, singer, and entrepreneur best known for her roles in soap operas such as "One Life to Live" and for her work as a professional hypnotist.
  • C. Catherine Petkoff
    Catherine Petkoff is a wealthy, socially ambitious Bulgarian matron in George Bernard Shaw’s play "Arms and the Man," known for her comic pretensions and concern with status.
  • D. Christina Fagan
    Christina Fagan is a notable individual recognized as a prominent bearer of the surname Fagan.
  • E. Catherine Corman
    Catherine Corman is a filmmaker and editor known for her work on art-house and experimental cinema projects.
  • 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: Catherine Faylen
Triple: [Regis Philbin, spouse, Catherine Faylen]
Generated description
Catherine Faylen is an American actress best known for her film and television roles in the 1940s and 1950s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Catherine Faylen
Target entity description: Catherine Faylen is an American actress best known for her film and television roles in the 1940s and 1950s.
  • A. Catherine Meyer
    Catherine Meyer is the socially awkward, long-suffering daughter of fictional U.S. Vice President and President Selina Meyer on the television series "Veep."
  • B. Catherine Hickland
    Catherine Hickland is an American actress, singer, and entrepreneur best known for her roles in soap operas such as "One Life to Live" and for her work as a professional hypnotist.
  • C. Catherine Petkoff
    Catherine Petkoff is a wealthy, socially ambitious Bulgarian matron in George Bernard Shaw’s play "Arms and the Man," known for her comic pretensions and concern with status.
  • D. Christina Fagan
    Christina Fagan is a notable individual recognized as a prominent bearer of the surname Fagan.
  • E. Catherine Corman
    Catherine Corman is a filmmaker and editor known for her work on art-house and experimental cinema projects.
  • 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_69d806b349908190a9a61dd9323bf153 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990759ebc8190a9487a59e37a69e2 completed April 11, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69f794202df08190acf1a7710b64198c completed May 3, 2026, 6:29 p.m.
NEDg Description generation batch_69f796a4eac88190aa68765fd0e6dfe7 completed May 3, 2026, 6:40 p.m.
NED2 Entity disambiguation (via description) batch_69f7976846308190b1a5c056609fca34 completed May 3, 2026, 6:43 p.m.
Created at: April 9, 2026, 9:27 p.m.