Triple

T13000520
Position Surface form Disambiguated ID Type / Status
Subject Mary (novel) E322156 entity
Predicate hasCharacter P2308 FINISHED
Object Joseph
Joseph is a fictional character in Vladimir Nabokov’s novel "Mary," playing a supporting role in the story’s exploration of memory and lost love.
E1015363 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: Joseph | Statement: [Mary (novel), hasCharacter, Joseph]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joseph
Context triple: [Mary (novel), hasCharacter, Joseph]
  • A. Joseph
    Joseph is the first name of J. C. R. Licklider, a pioneering computer scientist often regarded as a key figure in the development of the internet and interactive computing.
  • B. Joseph
    Joseph is the full given name of American sportscaster Joe Buck, known for his play-by-play announcing of major NFL and MLB games.
  • C. Joseph
    Joseph is a common masculine given name of Hebrew origin, traditionally interpreted to mean "He will add" or "God increases."
  • D. Joseph
    Joseph is the given name of the renowned British Romantic landscape painter J. M. W. Turner.
  • E. Joseph
    Joseph is the given first name of American voice actor and comedian Joe Alaskey, known for voicing several iconic Looney Tunes characters.
  • 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: Joseph
Triple: [Mary (novel), hasCharacter, Joseph]
Generated description
Joseph is a fictional character in Vladimir Nabokov’s novel "Mary," playing a supporting role in the story’s exploration of memory and lost love.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Joseph
Target entity description: Joseph is a fictional character in Vladimir Nabokov’s novel "Mary," playing a supporting role in the story’s exploration of memory and lost love.
  • A. Joseph
    Joseph is the given name of the iconic comic book character Judge Joseph Dredd, a law enforcement officer in the dystopian future city of Mega-City One.
  • B. Joseph
    Joseph is the husband of Mary in the New Testament and the earthly guardian of Jesus, venerated in Christianity as a model of humility, obedience, and fatherhood.
  • C. Joseph
    Joseph is the given first name of the 19th-century Irish Gothic writer Sheridan Le Fanu.
  • D. Joseph
    Joseph is the given name of Joe DiMaggio, the legendary American baseball center fielder for the New York Yankees.
  • E. Joseph
    Joseph is the middle name of the 19th-century American reformer and Unitarian minister Samuel Joseph May, known for his prominent role in the abolitionist and social reform movements.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e9828748190b2ad9ea29180b7d3 completed April 10, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c101ea60819098e4d5fb3a9e803a completed May 3, 2026, 3:29 a.m.
NEDg Description generation batch_69f6c277e6248190870b3bf9869716a7 completed May 3, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69f6c38bc0b08190b76cb0853d99ad82 completed May 3, 2026, 3:39 a.m.
Created at: April 9, 2026, 8:46 p.m.