Triple

T22506431
Position Surface form Disambiguated ID Type / Status
Subject Saul (Handel) E556400 entity
Predicate hasCharacter P2308 FINISHED
Object Doeg
Doeg is a biblical figure, an Edomite servant of King Saul known for betraying the priests of Nob, who is featured as a character in Handel’s oratorio "Saul."
E1540689 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: Doeg | Statement: [Saul (Handel), hasCharacter, Doeg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Doeg
Context triple: [Saul (Handel), hasCharacter, Doeg]
  • A. Blakiston
    Blakiston is an English surname historically associated with notable figures such as explorer and naturalist Thomas Blakiston.
  • B. Corvo
    Corvo is the smallest and northernmost island of the Azores archipelago in the North Atlantic Ocean, known for its volcanic landscape and remote, sparsely populated character.
  • C. Zajac
    Zajac is a surname most notably associated with former NHL center Travis Zajac, who spent the majority of his career with the New Jersey Devils.
  • D. Wolfe
    Wolfe is a surname most famously associated with British Army officer James Wolfe, known for his role in the Seven Years' War and the capture of Quebec.
  • E. Badger
    Badger is a fictional character appearing in the work "The Return of Ulysses."
  • 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: Doeg
Triple: [Saul (Handel), hasCharacter, Doeg]
Generated description
Doeg is a biblical figure, an Edomite servant of King Saul known for betraying the priests of Nob, who is featured as a character in Handel’s oratorio "Saul."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Doeg
Target entity description: Doeg is a biblical figure, an Edomite servant of King Saul known for betraying the priests of Nob, who is featured as a character in Handel’s oratorio "Saul."
  • A. Blakiston
    Blakiston is an English surname historically associated with notable figures such as explorer and naturalist Thomas Blakiston.
  • B. Corvo
    Corvo is the smallest and northernmost island of the Azores archipelago in the North Atlantic Ocean, known for its volcanic landscape and remote, sparsely populated character.
  • C. Zajac
    Zajac is a surname most notably associated with former NHL center Travis Zajac, who spent the majority of his career with the New Jersey Devils.
  • D. Wolfe
    Wolfe is a surname most famously associated with British Army officer James Wolfe, known for his role in the Seven Years' War and the capture of Quebec.
  • E. Badger
    Badger is a wise, kind, and somewhat reclusive character from Kenneth Grahame’s "The Wind in the Willows," known for offering guidance and shelter to his woodland friends.
  • 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_69e11e555edc81909ca803587dafd747 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15d5cddf88190821d9c9fdee84160 completed April 29, 2026, 1:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b17e860888190b5c74df43a9890e9 completed May 18, 2026, 1:45 p.m.
NEDg Description generation batch_6a0b18ad4f608190a6947aeb790d8be7 completed May 18, 2026, 1:48 p.m.
NED2 Entity disambiguation (via description) batch_6a0b1979fe088190a06edb086d6b2b46 completed May 18, 2026, 1:51 p.m.
Created at: April 16, 2026, 8:50 p.m.