Triple

T1818906
Position Surface form Disambiguated ID Type / Status
Subject Ben Affleck E40496 entity
Predicate directed P7373 FINISHED
Object Live by Night
Live by Night is a 2016 American crime drama film, based on Dennis Lehane’s novel, that follows a Prohibition-era gangster’s rise in the world of organized crime.
E204625 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: Live by Night | Statement: [Ben Affleck, directed, Live by Night]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Live by Night
Context triple: [Ben Affleck, directed, Live by Night]
  • A. Stay the Night
    "Stay the Night" is an R&B song by Mariah Carey from her 2005 album The Emancipation of Mimi, noted for its soulful vocals and contemporary production.
  • B. Stay the Night
    "Stay the Night" is a song by the American punk rock band Green Day from their album ¡Uno!.
  • C. Run All Night
    Run All Night is a 2015 action thriller film in which Liam Neeson plays an aging hitman forced to protect his estranged son over the course of one violent night.
  • D. The Night
    The Night is a haunting Expressionist painting by Max Beckmann that depicts the brutal terror and psychological trauma of a violent home invasion.
  • E. Save the Night
    "Save the Night" is a song by John Legend from his R&B album "Love in the Future."
  • 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: Live by Night
Triple: [Ben Affleck, directed, Live by Night]
Generated description
Live by Night is a 2016 American crime drama film, based on Dennis Lehane’s novel, that follows a Prohibition-era gangster’s rise in the world of organized crime.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Live by Night
Target entity description: Live by Night is a 2016 American crime drama film, based on Dennis Lehane’s novel, that follows a Prohibition-era gangster’s rise in the world of organized crime.
  • A. Stay the Night
    "Stay the Night" is an R&B song by Mariah Carey from her 2005 album The Emancipation of Mimi, noted for its soulful vocals and contemporary production.
  • B. Stay the Night
    "Stay the Night" is a song by the American punk rock band Green Day from their album ¡Uno!.
  • C. Run All Night
    Run All Night is a 2015 action thriller film in which Liam Neeson plays an aging hitman forced to protect his estranged son over the course of one violent night.
  • D. The Night
    The Night is a haunting Expressionist painting by Max Beckmann that depicts the brutal terror and psychological trauma of a violent home invasion.
  • E. Save the Night
    "Save the Night" is a song by John Legend from his R&B album "Love in the Future."
  • 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_69a8864526c081908a3a4d74f689e2c5 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa65f8c4e48190925aec9916dd6c30 completed March 6, 2026, 5:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69adbf629af48190a27fddc764e306a7 completed March 8, 2026, 6:26 p.m.
NEDg Description generation batch_69adc07e9ebc819082566cc98025b4ae completed March 8, 2026, 6:31 p.m.
NED2 Entity disambiguation (via description) batch_69adc1304a808190a999e71dfa39162a completed March 8, 2026, 6:34 p.m.
Created at: March 4, 2026, 7:32 p.m.