Triple

T6955710
Position Surface form Disambiguated ID Type / Status
Subject Frank Darabont E161237 entity
Predicate givenName P17 FINISHED
Object Frank
Frank is the given name of filmmaker Frank Darabont, the acclaimed director and screenwriter known for works such as The Shawshank Redemption and The Green Mile.
E630936 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: Frank | Statement: [Frank Darabont, givenName, Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank
Context triple: [Frank Darabont, givenName, Frank]
  • A. Frank
    Frank is a key supporting character in the post-apocalyptic horror film "28 Days Later," known as a protective father trying to keep his daughter safe amid a devastating viral outbreak in London.
  • B. Frank
    Frank is the given name of Frank Abagnale Jr., the infamous former con artist whose life inspired the film "Catch Me If You Can."
  • C. Frank
    Frank is the given name of British screenwriter and children's author Frank Cottrell-Boyce.
  • D. Frank
    Frank is the given name of British former professional heavyweight boxer Frank Bruno, a popular sports figure especially known in the UK.
  • E. Frank
    Frank is an alternate given name of longtime Republican U.S. Congressman Jim Sensenbrenner, who represented a Wisconsin district in the House of Representatives for four decades.
  • 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: Frank
Triple: [Frank Darabont, givenName, Frank]
Generated description
Frank is the given name of filmmaker Frank Darabont, the acclaimed director and screenwriter known for works such as The Shawshank Redemption and The Green Mile.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frank
Target entity description: Frank is the given name of filmmaker Frank Darabont, the acclaimed director and screenwriter known for works such as The Shawshank Redemption and The Green Mile.
  • A. Frank
    Frank is the given name of Frank Oz, the renowned puppeteer, actor, and director best known for his work with the Muppets and on Star Wars.
  • B. Frank
    Frank is the given name of Frank Abagnale Jr., the infamous former con artist whose life inspired the film "Catch Me If You Can."
  • C. Frank
    Frank is the given name of Frank Lampard, the renowned English former professional footballer and manager.
  • D. Frank
    Frank is the given name of the renowned Canadian-American architect Frank Gehry, celebrated for his deconstructivist and sculptural building designs.
  • E. Frank
    Frank is the given name of Frank País, a prominent Cuban revolutionary leader active during the Cuban Revolution.
  • 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_69c68852a9a0819097797e31d492e273 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dacf8c8c8190a25dbacebeb4b66e completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c75888d48c81908a8dbd16d7591b55 completed March 28, 2026, 4:26 a.m.
NEDg Description generation batch_69c7596571a48190a8a04b9b24b5e4cb completed March 28, 2026, 4:30 a.m.
NED2 Entity disambiguation (via description) batch_69c75a57dc308190a691d3ae55cc39ef completed March 28, 2026, 4:34 a.m.
Created at: March 27, 2026, 2:29 p.m.