Triple

T2478817
Position Surface form Disambiguated ID Type / Status
Subject Lady in the Dark E55154 entity
Predicate character P662 FINISHED
Object Randy Curtis
Randy Curtis is a fictional movie star character who appears as one of the romantic interests in the musical play and film "Lady in the Dark."
E269929 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: Randy Curtis | Statement: [Lady in the Dark, character, Randy Curtis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Randy Curtis
Context triple: [Lady in the Dark, character, Randy Curtis]
  • A. Curtis Craig
    Curtis Craig was the male college student who served as the named plaintiff challenging Oklahoma's gender-based drinking age law in the landmark U.S. Supreme Court case Craig v. Boren.
  • B. Steven Elliott
    Steven Elliott is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
  • C. Dan Jewett
    Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
  • D. Jeff Danna
    Jeff Danna is a Canadian film composer known for his scores for movies such as The Boondock Saints and various animated and dramatic films.
  • E. Chris Klein
    Chris Klein is a former American professional soccer player who later became a sports executive, notably serving as president of Major League Soccer’s LA Galaxy.
  • 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: Randy Curtis
Triple: [Lady in the Dark, character, Randy Curtis]
Generated description
Randy Curtis is a fictional movie star character who appears as one of the romantic interests in the musical play and film "Lady in the Dark."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Randy Curtis
Target entity description: Randy Curtis is a fictional movie star character who appears as one of the romantic interests in the musical play and film "Lady in the Dark."
  • A. Curtis Craig
    Curtis Craig was the male college student who served as the named plaintiff challenging Oklahoma's gender-based drinking age law in the landmark U.S. Supreme Court case Craig v. Boren.
  • B. Steven Elliott
    Steven Elliott is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
  • C. Dan Jewett
    Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
  • D. Jeff Danna
    Jeff Danna is a Canadian film composer known for his scores for movies such as The Boondock Saints and various animated and dramatic films.
  • E. Chris Klein
    Chris Klein is a former American professional soccer player who later became a sports executive, notably serving as president of Major League Soccer’s LA Galaxy.
  • 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_69ab49e279e88190ab10d7248aea9d11 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd15f95888190a94b5fef7fdf1bcb completed March 7, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69af17aea398819092cb14b93abd0ff7 completed March 9, 2026, 6:55 p.m.
NEDg Description generation batch_69af18f9af388190bbb4242c89d4272e completed March 9, 2026, 7:01 p.m.
NED2 Entity disambiguation (via description) batch_69af198534c0819090c742f39501fac6 completed March 9, 2026, 7:03 p.m.
Created at: March 6, 2026, 9:45 p.m.