Triple

T2283249
Position Surface form Disambiguated ID Type / Status
Subject Gethsemane prayer E51326 entity
Predicate witnessedBy P1165 FINISHED
Object John
John is traditionally regarded as one of Jesus’ closest disciples and the presumed author of the Gospel of John in the New Testament.
E167813 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: [Gethsemane prayer, witnessedBy, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [Gethsemane prayer, witnessedBy, John]
  • A. John
    John is traditionally regarded as the author of the New Testament’s Book of Revelation, a prophetic and apocalyptic text in Christian scripture.
  • B. John
    John is the given name of John Perry Barlow, the American poet, essayist, and co-founder of the Electronic Frontier Foundation known for his advocacy of digital rights.
  • C. 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.
  • D. 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.
  • 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: [Gethsemane prayer, witnessedBy, John]
Generated description
John is traditionally regarded as one of Jesus’ closest disciples and the presumed author of the Gospel of John in the New Testament.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John is traditionally regarded as one of Jesus’ closest disciples and the presumed author of the Gospel of John in the New Testament.
  • A. John
    John is traditionally regarded as the author of the New Testament’s Book of Revelation, a prophetic and apocalyptic text in Christian scripture.
  • B. John chosen
    John is one of the four canonical Gospels in the New Testament, presenting a distinct theological portrait of Jesus Christ with a strong emphasis on his divinity.
  • C. John
    John is the given name of John Stott, a prominent 20th-century English Anglican priest, theologian, and influential evangelical leader.
  • D. John
    John is the given name of the influential English philosopher John Locke, a key figure in empiricism and liberal political theory.
  • E. John
    John is the given name of John Proctor, a historical figure best known as a farmer executed during the Salem witch trials and later popularized as a central character in Arthur Miller’s play "The Crucible."
  • 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_69a88b08e4308190bdac9aebcca1c91a completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc21d6d748190980128c1bc5b9621 completed March 7, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebeee5a808190981c06b78d30f004 completed March 9, 2026, 12:37 p.m.
NEDg Description generation batch_69aec43352d88190a4e9ae4f315938db completed March 9, 2026, 12:59 p.m.
NED2 Entity disambiguation (via description) batch_69aec4adb21c8190a89d53588ad75438 completed March 9, 2026, 1:01 p.m.
Created at: March 4, 2026, 7:48 p.m.