Triple

T5334370
Position Surface form Disambiguated ID Type / Status
Subject John Derek E123789 entity
Predicate givenName P17 FINISHED
Object John
John Derek was an American actor, director, and photographer known for his film roles in the 1940s–1960s and for directing and photographing his wife Bo Derek.
E512719 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 | Statement: [John Derek, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Derek, givenName, John]
  • A. John
    John is the given name of the renowned British mathematician John H. Conway, known for his work in group theory, number theory, and the invention of the Game of Life.
  • B. John
    John is the given name of John Nance Garner, who served as the 32nd vice president of the United States under President Franklin D. Roosevelt.
  • C. John
    John is the given first name of J. Michael Bishop, the American immunologist and Nobel Prize–winning scientist known for his work on oncogenes.
  • D. John
    John is the given name of John H. Hammond Jr., the influential American record producer and talent scout known for discovering and promoting numerous major jazz, blues, and rock musicians.
  • E. John
    John is the given name of John F. Sattler, likely referring to him in a more informal or abbreviated context.
  • 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
Triple: [John Derek, givenName, John]
Generated description
John Derek was an American actor, director, and photographer known for his film roles in the 1940s–1960s and for directing and photographing his wife Bo Derek.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John Derek was an American actor, director, and photographer known for his film roles in the 1940s–1960s and for directing and photographing his wife Bo Derek.
  • A. John
    John is the birth name of Jack Pickford, a Canadian-born American actor and film director of the silent era and younger brother of Mary Pickford.
  • B. John
    John is the birth name of American actor and filmmaker Jack Nicholson, one of cinema’s most acclaimed and iconic performers.
  • C. John
    John is the birth name of American actor Jack Lemmon, a celebrated star of classic films such as "Some Like It Hot" and "The Apartment."
  • D. John
    John is the first name of American filmmaker John Lee Hancock, known for directing and writing several popular Hollywood films.
  • E. John
    John is the given name of the late American comedian and actor John Belushi, famed for his work on "Saturday Night Live" and in films like "Animal House" and "The Blues Brothers."
  • 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_69bd464b07f8819095aa76577c9829e4 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85ae52c08190968a5567b7e6b794 completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf188394ec81909a03afe92750e9c1 completed March 21, 2026, 10:15 p.m.
NEDg Description generation batch_69bf1c6c84b481909c7e650c58961bd7 completed March 21, 2026, 10:32 p.m.
NED2 Entity disambiguation (via description) batch_69bf1cce6f9881908499ac380f183ffb completed March 21, 2026, 10:33 p.m.
Created at: March 20, 2026, 2 p.m.