Triple

T4623239
Position Surface form Disambiguated ID Type / Status
Subject The Fortune Cookie E101034 entity
Predicate mainCharacter P1183 FINISHED
Object Willie Gingrich
Willie Gingrich is a fast-talking, opportunistic lawyer character from Billy Wilder’s film "The Fortune Cookie," famously portrayed by Walter Matthau.
E456977 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: Willie Gingrich | Statement: [The Fortune Cookie, mainCharacter, Willie Gingrich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Willie Gingrich
Context triple: [The Fortune Cookie, mainCharacter, Willie Gingrich]
  • A. Arnold Gingrich
    Arnold Gingrich was an American magazine editor best known as a co-founder and longtime editor of the influential men's magazine Esquire.
  • B. Joseph W. Byrns
    Joseph W. Byrns was an American Democratic politician from Tennessee who served as Speaker of the U.S. House of Representatives in the mid-1930s.
  • C. Milton Moore
    Milton Moore was a cinematographer active during the silent film era, known for his work on early American cinema.
  • D. Bill Hagerty
    Bill Hagerty is a Republican politician and former U.S. ambassador to Japan who serves as a United States Senator from Tennessee.
  • E. Lawrence A. Maddox
    Lawrence A. Maddox is a film editor best known for his work on genre films such as the horror-western From Dusk Till Dawn 3: The Hangman's Daughter.
  • 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: Willie Gingrich
Triple: [The Fortune Cookie, mainCharacter, Willie Gingrich]
Generated description
Willie Gingrich is a fast-talking, opportunistic lawyer character from Billy Wilder’s film "The Fortune Cookie," famously portrayed by Walter Matthau.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Willie Gingrich
Target entity description: Willie Gingrich is a fast-talking, opportunistic lawyer character from Billy Wilder’s film "The Fortune Cookie," famously portrayed by Walter Matthau.
  • A. Arnold Gingrich
    Arnold Gingrich was an American magazine editor best known as a co-founder and longtime editor of the influential men's magazine Esquire.
  • B. Joseph W. Byrns
    Joseph W. Byrns was an American Democratic politician from Tennessee who served as Speaker of the U.S. House of Representatives in the mid-1930s.
  • C. Milton Moore
    Milton Moore was a cinematographer active during the silent film era, known for his work on early American cinema.
  • D. Bill Hagerty
    Bill Hagerty is a Republican politician and former U.S. ambassador to Japan who serves as a United States Senator from Tennessee.
  • E. Lawrence A. Maddox
    Lawrence A. Maddox is a film editor best known for his work on genre films such as the horror-western From Dusk Till Dawn 3: The Hangman's Daughter.
  • 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_69bd43d0497c8190ac23c65c5804846a completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a053d38819097b3ecbc06aa6e4d completed March 20, 2026, 2:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfaa069388190b6482315708b85c2 completed March 21, 2026, 1:55 a.m.
NEDg Description generation batch_69bdfb9422e48190819d5d99e72e8854 completed March 21, 2026, 1:59 a.m.
NED2 Entity disambiguation (via description) batch_69bdfc6ac91c819090776365d3dc05d4 completed March 21, 2026, 2:03 a.m.
Created at: March 20, 2026, 1:12 p.m.