Triple

T9578970
Position Surface form Disambiguated ID Type / Status
Subject The Exes E231119 entity
Predicate mainCharacter P1183 FINISHED
Object Haskell Lutz
Haskell Lutz is a quirky, scheming divorce attorney and one of the central comedic characters on the sitcom "The Exes."
E817684 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: Haskell Lutz | Statement: [The Exes, mainCharacter, Haskell Lutz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haskell Lutz
Context triple: [The Exes, mainCharacter, Haskell Lutz]
  • A. Paul Madvig
    Paul Madvig is the politically connected fixer and central protagonist of the 1942 film noir "The Glass Key," navigating corruption, loyalty, and murder in a tense urban underworld.
  • B. Louis Lingg
    Louis Lingg was a German-born anarchist and labor activist best known as one of the defendants in the 1886 Haymarket affair in Chicago.
  • C. William Wendt
    William Wendt was a prominent American landscape painter celebrated as a leading figure of the California Impressionist movement.
  • D. Max Lindauer
    Max Lindauer is an individual notable enough to be recognized as a prominent bearer of the surname Lindauer.
  • E. Edward Anhalt
    Edward Anhalt was an American screenwriter and producer best known for his Academy Award–winning work on films such as "Panic in the Streets" and "Becket."
  • 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: Haskell Lutz
Triple: [The Exes, mainCharacter, Haskell Lutz]
Generated description
Haskell Lutz is a quirky, scheming divorce attorney and one of the central comedic characters on the sitcom "The Exes."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haskell Lutz
Target entity description: Haskell Lutz is a quirky, scheming divorce attorney and one of the central comedic characters on the sitcom "The Exes."
  • A. Paul Madvig
    Paul Madvig is the politically connected fixer and central protagonist of the 1942 film noir "The Glass Key," navigating corruption, loyalty, and murder in a tense urban underworld.
  • B. Louis Lingg
    Louis Lingg was a German-born anarchist and labor activist best known as one of the defendants in the 1886 Haymarket affair in Chicago.
  • C. William Wendt
    William Wendt was a prominent American landscape painter celebrated as a leading figure of the California Impressionist movement.
  • D. Max Lindauer
    Max Lindauer is an individual notable enough to be recognized as a prominent bearer of the surname Lindauer.
  • E. Edward Anhalt
    Edward Anhalt was an American screenwriter and producer best known for his Academy Award–winning work on films such as "Panic in the Streets" and "Becket."
  • 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_69ca848091c48190bc313d6620d09555 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99aece1081908287e03106de020f completed April 1, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1af53434c8190a93fec3538730d58 completed April 5, 2026, 12:39 a.m.
NEDg Description generation batch_69d1b1a340d481908de95f04fcdd3bdd completed April 5, 2026, 12:49 a.m.
NED2 Entity disambiguation (via description) batch_69d1b2167d38819087f111e789cfc339 completed April 5, 2026, 12:51 a.m.
Created at: March 30, 2026, 8:05 p.m.