Triple

T20820199
Position Surface form Disambiguated ID Type / Status
Subject Frank Bledsoe E512554 entity
Predicate partnerNicknameFor P68532 FINISHED
Object Wally
Wally is the romantic partner of Frank Bledsoe in the film "Uncle Frank."
E1453215 NE FINISHED

How this triple was built (5 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: Wally | Statement: [Frank Bledsoe, partnerNicknameFor, Wally]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wally
Context triple: [Frank Bledsoe, partnerNicknameFor, Wally]
  • A. Wally
    Wally is a character from the comedy film "The Great Outdoors," known for his role in the movie’s humorous family vacation mishaps.
  • B. Wally
    Wally, better known as Numbuh 4, is a hot-headed, tough but loyal member of the Kids Next Door from the animated series "Codename: Kids Next Door."
  • C. Wally
    Wally is a character featured in the educational children's series "Alphabetical Order," likely serving as a playful figure to help teach letters and literacy concepts.
  • D. Wally
    Wally is a common English diminutive given name, typically derived from names like Walter or Waldemar.
  • E. Wally
    Wally is a perpetually lazy, coffee-loving office worker from the "Dilbert" comic strip, known for his extreme apathy and talent for avoiding work.
  • 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: Wally
Triple: [Frank Bledsoe, partnerNicknameFor, Wally]
Generated description
Wally is the romantic partner of Frank Bledsoe in the film "Uncle Frank."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Wally
Target entity description: Wally is the romantic partner of Frank Bledsoe in the film "Uncle Frank."
  • A. Wally
    Wally is a character featured in the educational children's series "Alphabetical Order," likely serving as a playful figure to help teach letters and literacy concepts.
  • B. Wally
    Wally is a common English diminutive given name, typically derived from names like Walter or Waldemar.
  • C. Wally
    Wally is a character from the comedy film "The Great Outdoors," known for his role in the movie’s humorous family vacation mishaps.
  • D. Wally
    Wally, better known as Numbuh 4, is a hot-headed, tough but loyal member of the Kids Next Door from the animated series "Codename: Kids Next Door."
  • E. Wally
    Wally is a perpetually lazy, coffee-loving office worker from the "Dilbert" comic strip, known for his extreme apathy and talent for avoiding work.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: partnerNicknameFor
Context triple: [Frank Bledsoe, partnerNicknameFor, Wally]
  • A. partnerInOrganizationWith
    Indicates that two entities are associated as partners within the same organization or organizational context.
  • B. partnerInCreation
    Indicates that two or more entities collaborated as partners in bringing something into existence or producing it.
  • C. cooperationPartner
    Indicates that two entities are engaged in a collaborative relationship, working together toward shared goals or mutual benefit.
  • D. partnerNation
    Indicates that one entity is recognized as a collaborating or allied nation in relation to another entity.
  • E. partnerCodename chosen
    Indicates that one entity is associated with another entity through a designated partner-specific codename or alias.
  • F. None of above.

Provenance (6 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_69e0b4ce39108190a6e8e5df4f1c8dc5 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2f6a65481909a0df78616e185e4 completed April 21, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a090077c1b4819097e2023cb63b3bb3 completed May 16, 2026, 11:40 p.m.
NEDg Description generation batch_6a0904888aa48190983a7102b22e9654 completed May 16, 2026, 11:58 p.m.
NED2 Entity disambiguation (via description) batch_6a0908594c3881909c7ef81dfb002c6f completed May 17, 2026, 12:14 a.m.
PD Predicate disambiguation batch_69e5c99ca55481908e8d434fa901cfd6 completed April 20, 2026, 6:37 a.m.
Created at: April 16, 2026, 12:41 p.m.