Triple

T14710201
Position Surface form Disambiguated ID Type / Status
Subject Jumanji (1981 book) E345527 entity
Predicate mainCharacter P1183 FINISHED
Object Peter
Peter is the young protagonist of the 1981 children's fantasy picture book "Jumanji" by Chris Van Allsburg, whose discovery of a mysterious board game unleashes magical chaos.
E1115082 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: Peter | Statement: [Jumanji (1981 book), mainCharacter, Peter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter
Context triple: [Jumanji (1981 book), mainCharacter, Peter]
  • A. Peter
    Peter was one of the leaders of the late 12th-century Bulgarian uprising that restored the Bulgarian Empire against Byzantine rule.
  • B. Peter
    Peter is a recurring comedic character from the British sketch show "A Bit of Fry & Laurie."
  • C. Peter
    Peter is a central character in the Australian television drama series "The Newsreader," which follows the turbulent personal and professional lives of 1980s newsroom staff.
  • D. Peter
    Peter is a common male given name of Greek origin, widely used in many languages and cultures, often associated with the meaning "rock" or "stone."
  • E. Peter
    Peter is a central character in Margaret Atwood's novel "The Edible Woman," serving as the protagonist Marian's conventional, marriage-minded fiancé who embodies societal expectations.
  • 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: Peter
Triple: [Jumanji (1981 book), mainCharacter, Peter]
Generated description
Peter is the young protagonist of the 1981 children's fantasy picture book "Jumanji" by Chris Van Allsburg, whose discovery of a mysterious board game unleashes magical chaos.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Peter
Target entity description: Peter is the young protagonist of the 1981 children's fantasy picture book "Jumanji" by Chris Van Allsburg, whose discovery of a mysterious board game unleashes magical chaos.
  • A. Peter
    Peter is a recurring child character in Enid Blyton’s “Wishing-Chair” fantasy series, known for his magical adventures involving a flying chair.
  • B. Peter
    Peter is the young, adventurous orphan who becomes the boy that never grows up in the Peter and the Starcatcher prequel to the Peter Pan story.
  • C. Peter
    Peter is a character known as a friend and companion of Chinky the pixie in children's fantasy stories.
  • D. Peter
    Peter is the young prince falsely accused of murder and imprisoned in Stephen King’s fantasy novel "The Eyes of the Dragon," whose struggle to reclaim his throne drives the story.
  • E. Peter
    Peter is the sensible and responsible leader of Enid Blyton’s Secret Seven children’s detective club.
  • 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_69d822e4a8c08190a155df736bb7bc13 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb9814e0c8190984ac30d276499cc completed April 14, 2026, 10:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf08d59b48190a1ddd2aed6ed756e completed May 8, 2026, 2:17 p.m.
NEDg Description generation batch_69fdf2728df881909609d4e6177c7841 completed May 8, 2026, 2:25 p.m.
NED2 Entity disambiguation (via description) batch_69fdf30dab20819085589da4e869fb7e completed May 8, 2026, 2:28 p.m.
Created at: April 10, 2026, 1:28 a.m.