Triple

T21429027
Position Surface form Disambiguated ID Type / Status
Subject Ice Castles E528633 entity
Predicate character P662 FINISHED
Object Beulah Smith
Beulah Smith is a fictional character from the romantic drama film "Ice Castles."
E1491279 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: Beulah Smith | Statement: [Ice Castles, character, Beulah Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beulah Smith
Context triple: [Ice Castles, character, Beulah Smith]
  • A. Beulah Brown
    Beulah Brown is the central housekeeper character from the mid-20th-century American radio and television comedy series "Beulah."
  • B. Otelia Cox
    Otelia Cox is the wife of American actor Tony Cox, known for his roles in films such as "Bad Santa" and "Me, Myself & Irene."
  • C. Della Smith
    Della Smith is a character in the political thriller film "State of Play," where she works as a journalist alongside Cal McCaffrey.
  • D. Beulah Marie Dix
    Beulah Marie Dix was an American playwright, novelist, and screenwriter active in the early 20th century, known for her historical dramas and contributions to silent and early sound films.
  • E. Edna Mae McCauley
    Edna Mae McCauley is the central character in the 1980 drama film "Resurrection," a woman who miraculously survives a near-fatal accident and discovers she has the power to heal others.
  • 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: Beulah Smith
Triple: [Ice Castles, character, Beulah Smith]
Generated description
Beulah Smith is a fictional character from the romantic drama film "Ice Castles."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Beulah Smith
Target entity description: Beulah Smith is a fictional character from the romantic drama film "Ice Castles."
  • A. Beulah Brown
    Beulah Brown is the central housekeeper character from the mid-20th-century American radio and television comedy series "Beulah."
  • B. Otelia Cox
    Otelia Cox is the wife of American actor Tony Cox, known for his roles in films such as "Bad Santa" and "Me, Myself & Irene."
  • C. Della Smith
    Della Smith is a character in the political thriller film "State of Play," where she works as a journalist alongside Cal McCaffrey.
  • D. Beulah Marie Dix
    Beulah Marie Dix was an American playwright, novelist, and screenwriter active in the early 20th century, known for her historical dramas and contributions to silent and early sound films.
  • E. Edna Mae McCauley
    Edna Mae McCauley is the central character in the 1980 drama film "Resurrection," a woman who miraculously survives a near-fatal accident and discovers she has the power to heal others.
  • 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_69e0c455f3688190810bc96365791b0f completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee813db52c8190ac933bc6ec4dbf77 completed April 26, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a09f65fa1308190915373f77c5b19de completed May 17, 2026, 5:09 p.m.
NEDg Description generation batch_6a09f73007048190b9fc03f5d800ba84 completed May 17, 2026, 5:13 p.m.
NED2 Entity disambiguation (via description) batch_6a09f8149a84819085d07e5b1eea463f completed May 17, 2026, 5:17 p.m.
Created at: April 16, 2026, 5:49 p.m.