Triple

T21634632
Position Surface form Disambiguated ID Type / Status
Subject John Oliver E533923 entity
Predicate givenName P17 FINISHED
Object John
John is the given name of British-American comedian and television host John Oliver, best known for his satirical news show "Last Week Tonight with John Oliver."
E533923 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 Oliver, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John Oliver, givenName, John]
  • A. John
    John Vassall Jr. was a British civil servant who became notorious as a Soviet spy during the Cold War.
  • B. John
    John is the given name of John A. Roebling II, an American civil engineer and philanthropist from the prominent Roebling family associated with major bridge construction.
  • C. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • D. John
    John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
  • E. John
    John is the given name of John George Graves, a notable British mail-order entrepreneur and philanthropist from Sheffield.
  • 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 Oliver, givenName, John]
Generated description
John is the given name of British-American comedian and television host John Oliver, best known for his satirical news show "Last Week Tonight with John Oliver."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is the given name of British-American comedian and television host John Oliver, best known for his satirical news show "Last Week Tonight with John Oliver."
  • A. John chosen
    John is the given name of British-American comedian and television host John Oliver, best known for his satirical news show "Last Week Tonight with John Oliver."
  • B. John
    John is the given name of American stand-up comedian, writer, and actor John Mulaney, known for his sharp observational humor and work on Saturday Night Live.
  • C. John
    John is the given name of English comedian, actor, and writer John Cleese, a founding member of the legendary comedy group Monty Python.
  • D. 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."
  • E. John
    John is the first name of American comedian and actor Will Ferrell, known for his work on Saturday Night Live and numerous comedy films.
  • F. None of above.

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_69e0c465ae7481908577b7209fdb2a77 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef52192e388190a3f316e33f452561 completed April 27, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a0f8a69848190a4881bddc0fc3317 completed May 17, 2026, 6:57 p.m.
NEDg Description generation batch_6a0a1020e67c8190a6faf7e8e458d48e completed May 17, 2026, 6:59 p.m.
NED2 Entity disambiguation (via description) batch_6a0a10ac13288190a1fbf21fa67a4ed2 completed May 17, 2026, 7:02 p.m.
Created at: April 16, 2026, 6:35 p.m.