Triple

T23018538
Position Surface form Disambiguated ID Type / Status
Subject The Locket E573100 entity
Predicate character P662 FINISHED
Object John Willis
John Willis is a fictional character from the 1946 romantic drama film "The Locket."
 E1570433 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: John Willis | Statement: [The Locket, character, John Willis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Willis
Context triple: [The Locket, character, John Willis]
  • A. John Willis
    John Willis was a senior Royal Air Force officer who served as Air Officer Commanding-in-Chief of Fighter Command.
  • B. John Willis
    John Willis was an early settler and community leader credited with establishing the town that became Lumberton, North Carolina.
  • C. John Willis
    John Willis was an American theater historian and publisher best known as the longtime editor of Theatre World and the founder of the American Theater Hall of Fame.
  • D. Nat Willis
    Nat Willis is known primarily as the husband of British-American actress Andrea King.
  • E. Dave Willis
    Dave Willis is an American writer, voice actor, and producer best known for co-creating the Adult Swim animated series Aqua Teen Hunger Force and other surreal comedy shows.
  • 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: John Willis
Triple: [The Locket, character, John Willis]
Generated description
John Willis is a fictional character from the 1946 romantic drama film "The Locket."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John Willis
Target entity description: John Willis is a fictional character from the 1946 romantic drama film "The Locket."
  • A. John Willis
    John Willis was a senior Royal Air Force officer who served as Air Officer Commanding-in-Chief of Fighter Command.
  • B. John Willis
    John Willis was an early settler and community leader credited with establishing the town that became Lumberton, North Carolina.
  • C. John Willis
    John Willis was an American theater historian and publisher best known as the longtime editor of Theatre World and the founder of the American Theater Hall of Fame.
  • D. Nat Willis
    Nat Willis is known primarily as the husband of British-American actress Andrea King.
  • E. Dave Willis
    Dave Willis is an American writer, voice actor, and producer best known for co-creating the Adult Swim animated series Aqua Teen Hunger Force and other surreal comedy shows.
  • 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e64a4c8190b8d29ed638c7fef8 completed April 29, 2026, 4:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c159dd33881909a7cf4c1c218ba33 completed May 19, 2026, 7:47 a.m.
NEDg Description generation batch_6a0c19ba2cd88190aeffda94f9c2c361 completed May 19, 2026, 8:05 a.m.
NED2 Entity disambiguation (via description) batch_6a0c1b6bad048190ad23d93e3f95a75d completed May 19, 2026, 8:12 a.m.
Created at: April 17, 2026, 3:52 p.m.