Triple

T16441593
Position Surface form Disambiguated ID Type / Status
Subject Models Inc. E399313 entity
Predicate character P662 FINISHED
Object Sarah Owens
Sarah Owens is a fictional character from the television series "Models Inc.," a spin-off of "Melrose Place" set in the world of a Los Angeles modeling agency.
E1239171 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: Sarah Owens | Statement: [Models Inc., character, Sarah Owens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Owens
Context triple: [Models Inc., character, Sarah Owens]
  • A. Mary Owens
    Mary Owens was the wife of George Tyler Wood, the second Governor of Texas.
  • B. Sarah Owen
    Sarah Owen is a British woman best known as the sister of actor Alfie Allen and daughter of actor Keith Allen and film producer Alison Owen.
  • C. Sarah Winston
    Sarah Winston was a colonial American woman best known as the mother of Founding Father and second U.S. President John Adams.
  • D. Sophie Owens
    Sophie Owens is a fictional character appearing in the work "Closing Time."
  • E. Sandy Owens
    Sandy Owens is a central character in the 1950 Western film "Wagon Master," portrayed as one of the key figures in the story of a wagon train journey across the American frontier.
  • 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: Sarah Owens
Triple: [Models Inc., character, Sarah Owens]
Generated description
Sarah Owens is a fictional character from the television series "Models Inc.," a spin-off of "Melrose Place" set in the world of a Los Angeles modeling agency.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarah Owens
Target entity description: Sarah Owens is a fictional character from the television series "Models Inc.," a spin-off of "Melrose Place" set in the world of a Los Angeles modeling agency.
  • A. Mary Owens
    Mary Owens was the wife of George Tyler Wood, the second Governor of Texas.
  • B. Sarah Owen
    Sarah Owen is a British woman best known as the sister of actor Alfie Allen and daughter of actor Keith Allen and film producer Alison Owen.
  • C. Sarah Winston
    Sarah Winston was a colonial American woman best known as the mother of Founding Father and second U.S. President John Adams.
  • D. Sophie Owens
    Sophie Owens is a fictional character appearing in the work "Closing Time."
  • E. Sandy Owens
    Sandy Owens is a central character in the 1950 Western film "Wagon Master," portrayed as one of the key figures in the story of a wagon train journey across the American frontier.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba91dc48190bc35db60f63d36d3 completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00c794355881908fdec356d12a5635 completed May 10, 2026, 5:59 p.m.
NEDg Description generation batch_6a00c820f0a0819084348f8490d6c7e5 completed May 10, 2026, 6:02 p.m.
NED2 Entity disambiguation (via description) batch_6a00c88213988190b2d8f80d0fa9d15f completed May 10, 2026, 6:03 p.m.
Created at: April 10, 2026, 5:10 a.m.