Triple

T12090176
Position Surface form Disambiguated ID Type / Status
Subject The Long Firm E287920 entity
Predicate character P662 FINISHED
Object Lenny
Lenny is a fictional character from Jake Arnott’s crime novel "The Long Firm," set in London’s 1960s underworld.
 E962517 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: Lenny | Statement: [The Long Firm, character, Lenny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lenny
Context triple: [The Long Firm, character, Lenny]
  • A. Lenny
    "Lenny" is a 2001 rock album by American musician Lenny Kravitz, showcasing his blend of classic rock, funk, and soul influences.
  • B. Lenny
    Lenny is a science fiction short story by Isaac Asimov, featuring one of his early robot characters and exploring themes of robotics and human-robot interaction.
  • C. Lenny
    Lenny is the nickname and given name of Lenny Belardo, the fictional young American pope from the television series "The Young Pope."
  • D. Lenny
    Lenny is a character in Stephen Adly Guirgis's gritty stage play "In Arabia We'd All Be Kings," which explores the lives of struggling New Yorkers in a rapidly gentrifying Hell's Kitchen.
  • E. Lenny
    Lenny is a given name, often used as a diminutive form of Leonard or similar names.
  • 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: Lenny
Triple: [The Long Firm, character, Lenny]
Generated description
Lenny is a fictional character from Jake Arnott’s crime novel "The Long Firm," set in London’s 1960s underworld.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lenny
Target entity description: Lenny is a fictional character from Jake Arnott’s crime novel "The Long Firm," set in London’s 1960s underworld.
  • A. Lenny
    Lenny is a character in Stephen Adly Guirgis's gritty stage play "In Arabia We'd All Be Kings," which explores the lives of struggling New Yorkers in a rapidly gentrifying Hell's Kitchen.
  • B. Lenny
    Lenny is the nickname and given name of Lenny Belardo, the fictional young American pope from the television series "The Young Pope."
  • C. Lenny
    Lenny is a science fiction short story by Isaac Asimov, featuring one of his early robot characters and exploring themes of robotics and human-robot interaction.
  • D. Lenny
    Lenny is a given name, often used as a diminutive form of Leonard or similar names.
  • E. Lenny
    Lenny is a 1974 American biographical drama film about controversial comedian Lenny Bruce, directed by Bob Fosse and starring Dustin Hoffman.
  • 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_69d6ab4964708190850585628b287b0c completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915161f848190a6355c1e372eadaa completed April 10, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f66b2eb48190bae469d1dd82b119 completed May 2, 2026, 1:04 p.m.
NEDg Description generation batch_69f5fd79da748190b3f0dd7d7a46314d completed May 2, 2026, 1:34 p.m.
NED2 Entity disambiguation (via description) batch_69f5feeeeb2081908191b1c2d1c2fbfd completed May 2, 2026, 1:41 p.m.
Created at: April 8, 2026, 9:48 p.m.