Triple

T6962806
Position Surface form Disambiguated ID Type / Status
Subject Moth Smoke E161414 entity
Predicate mainCharacter P1183 FINISHED
Object Daru Shezad
Daru Shezad is the disillusioned, downward-spiraling protagonist of Mohsin Hamid’s novel "Moth Smoke," set against the backdrop of contemporary Lahore’s social and economic inequalities.
E630511 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: Daru Shezad | Statement: [Moth Smoke, mainCharacter, Daru Shezad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Daru Shezad
Context triple: [Moth Smoke, mainCharacter, Daru Shezad]
  • A. Arif Masood
    Arif Masood is a Pakistani architect best known for designing the iconic Pakistan Monument in Islamabad.
  • B. Abdul Mateen
    Abdul Mateen is a Bruneian prince and public figure known for his military career, international diplomacy, and prominent presence in regional and global events.
  • C. Raza Jaffrey
    Raza Jaffrey is a British actor and singer known for his roles in television series such as "Smash," "Homeland," and "Spooks" (MI-5).
  • D. Fahran Khan
    Fahran Khan is a writer known for contributing to the song "Dirrty."
  • E. Aasif Mandvi
    Aasif Mandvi is a British-American actor, comedian, and writer best known for his work as a correspondent on The Daily Show and for roles in film, television, and theater.
  • 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: Daru Shezad
Triple: [Moth Smoke, mainCharacter, Daru Shezad]
Generated description
Daru Shezad is the disillusioned, downward-spiraling protagonist of Mohsin Hamid’s novel "Moth Smoke," set against the backdrop of contemporary Lahore’s social and economic inequalities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Daru Shezad
Target entity description: Daru Shezad is the disillusioned, downward-spiraling protagonist of Mohsin Hamid’s novel "Moth Smoke," set against the backdrop of contemporary Lahore’s social and economic inequalities.
  • A. Arif Masood
    Arif Masood is a Pakistani architect best known for designing the iconic Pakistan Monument in Islamabad.
  • B. Abdul Mateen
    Abdul Mateen is a Bruneian prince and public figure known for his military career, international diplomacy, and prominent presence in regional and global events.
  • C. Raza Jaffrey
    Raza Jaffrey is a British actor and singer known for his roles in television series such as "Smash," "Homeland," and "Spooks" (MI-5).
  • D. Fahran Khan
    Fahran Khan is a writer known for contributing to the song "Dirrty."
  • E. Aasif Mandvi
    Aasif Mandvi is a British-American actor, comedian, and writer best known for his work as a correspondent on The Daily Show and for roles in film, television, and theater.
  • 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_69c68853cff881908439d488924a8283 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6daf197b0819085bd0433c8a7f716 completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7589c587c8190b97523b5ac2ab958 completed March 28, 2026, 4:27 a.m.
NEDg Description generation batch_69c759553fe081909881c8d2ae680dfe completed March 28, 2026, 4:30 a.m.
NED2 Entity disambiguation (via description) batch_69c759c79de48190bd3e079c07a9158a completed March 28, 2026, 4:32 a.m.
Created at: March 27, 2026, 2:30 p.m.