Triple

T2035541
Position Surface form Disambiguated ID Type / Status
Subject Ken Jeong E44616 entity
Predicate characterPortrayed P1507 FINISHED
Object Leslie Chow
Leslie Chow is a wildly eccentric, foul-mouthed, and unpredictable gangster character from The Hangover film series, known for his outrageous antics and chaotic energy.
 E232088 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: Leslie Chow | Statement: [Ken Jeong, characterPortrayed, Leslie Chow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Leslie Chow
Context triple: [Ken Jeong, characterPortrayed, Leslie Chow]
  • A. Kelly Chan
    Kelly Chan is a Hong Kong Cantopop singer and actress known for her popularity in the late 1990s and 2000s.
  • B. Vivian Chan
    Vivian Chan is a personal name shared by multiple individuals, including professionals in fields such as science, media, and business.
  • C. Lai-Sang Young
    Lai-Sang Young is a prominent mathematician known for her influential work in dynamical systems and ergodic theory.
  • D. Anita Chan
    Anita Chan is a prominent scholar known for her influential research on Chinese labor issues and labor rights.
  • E. Alex Tse
    Alex Tse is an American screenwriter and producer best known for co-writing the film adaptation of the graphic novel "Watchmen."
  • 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: Leslie Chow
Triple: [Ken Jeong, characterPortrayed, Leslie Chow]
Generated description
Leslie Chow is a wildly eccentric, foul-mouthed, and unpredictable gangster character from The Hangover film series, known for his outrageous antics and chaotic energy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Leslie Chow
Target entity description: Leslie Chow is a wildly eccentric, foul-mouthed, and unpredictable gangster character from The Hangover film series, known for his outrageous antics and chaotic energy.
  • A. Kelly Chan
    Kelly Chan is a Hong Kong Cantopop singer and actress known for her popularity in the late 1990s and 2000s.
  • B. Vivian Chan
    Vivian Chan is a personal name shared by multiple individuals, including professionals in fields such as science, media, and business.
  • C. Lai-Sang Young
    Lai-Sang Young is a prominent mathematician known for her influential work in dynamical systems and ergodic theory.
  • D. Anita Chan
    Anita Chan is a prominent scholar known for her influential research on Chinese labor issues and labor rights.
  • E. Alex Tse
    Alex Tse is an American screenwriter and producer best known for co-writing the film adaptation of the graphic novel "Watchmen."
  • 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_69a889159ec481908f9e4472d9f480c7 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb934ff948190acd88d4f587463a4 completed March 7, 2026, 5:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae2710f6408190b7feb99efa7ce9bb completed March 9, 2026, 1:49 a.m.
NEDg Description generation batch_69ae2a45abe4819096505781d6b27bd3 completed March 9, 2026, 2:02 a.m.
NED2 Entity disambiguation (via description) batch_69ae2b0e84108190ab2c0f356836a45c completed March 9, 2026, 2:06 a.m.
Created at: March 4, 2026, 7:39 p.m.