Triple

T14173218
Position Surface form Disambiguated ID Type / Status
Subject Howard Berger E351262 entity
Predicate notableWork P4 FINISHED
Object The Green Mile
The Green Mile is a 1999 American fantasy crime drama film directed by Frank Darabont, based on Stephen King’s novel about a death row corrections officer who witnesses miraculous events surrounding a gentle, supernaturally gifted inmate.
E37262 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: The Green Mile | Statement: [Howard Berger, notableWork, The Green Mile]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Green Mile
Context triple: [Howard Berger, notableWork, The Green Mile]
  • A. The Green Mile
    The Green Mile is a serialized novel by Stephen King that blends supernatural elements with a poignant death-row drama set in a 1930s Southern prison.
  • B. Kind Things
    "Kind Things" is a song by the indie rock band LNZNDRF, a side project featuring members of The National and Beirut known for their atmospheric, krautrock-influenced sound.
  • C. The Human Stain
    The Human Stain is a 2000 novel by Philip Roth that explores identity, race, and scandal in late-20th-century America through the downfall of a classics professor with a hidden past.
  • D. The Corrections
    The Corrections is a critically acclaimed novel by Jonathan Franzen that explores the complexities of a Midwestern American family at the turn of the 21st century.
  • E. The Executioner’s Song
    The Executioner’s Song is a Pulitzer Prize–winning nonfiction novel by Norman Mailer that chronicles the life, crimes, and execution of convicted murderer Gary Gilmore.
  • 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: The Green Mile
Triple: [Howard Berger, notableWork, The Green Mile]
Generated description
The Green Mile is a 1999 American fantasy crime drama film directed by Frank Darabont, based on Stephen King’s novel about a death row corrections officer who witnesses miraculous events surrounding a gentle, supernaturally gifted inmate.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: The Green Mile
Target entity description: The Green Mile is a 1999 American fantasy crime drama film directed by Frank Darabont, based on Stephen King’s novel about a death row corrections officer who witnesses miraculous events surrounding a gentle, supernaturally gifted inmate.
  • A. The Green Mile chosen
    The Green Mile is a serialized novel by Stephen King that blends supernatural elements with a poignant death-row drama set in a 1930s Southern prison.
  • B. Kind Things
    "Kind Things" is a song by the indie rock band LNZNDRF, a side project featuring members of The National and Beirut known for their atmospheric, krautrock-influenced sound.
  • C. The Human Stain
    The Human Stain is a 2000 novel by Philip Roth that explores identity, race, and scandal in late-20th-century America through the downfall of a classics professor with a hidden past.
  • D. The Corrections
    The Corrections is a critically acclaimed novel by Jonathan Franzen that explores the complexities of a Midwestern American family at the turn of the 21st century.
  • E. The Executioner’s Song
    The Executioner’s Song is a Pulitzer Prize–winning nonfiction novel by Norman Mailer that chronicles the life, crimes, and execution of convicted murderer Gary Gilmore.
  • F. None of above.

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_69d8278834a08190b0f1784e58d7b99c completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61b5dcbc8190b0cfcce5e6c6d582 completed April 14, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf80a9b34819081c4ebf7429e875a completed May 7, 2026, 8:37 p.m.
NEDg Description generation batch_69fd03511f048190a9f1eea0e37aef31 completed May 7, 2026, 9:25 p.m.
NED2 Entity disambiguation (via description) batch_69fd0406a770819082aeec43037f1243 completed May 7, 2026, 9:28 p.m.
Created at: April 10, 2026, 1:01 a.m.