Triple

T19206348
Position Surface form Disambiguated ID Type / Status
Subject John Thornton E480242 entity
Predicate travelsWith P881 FINISHED
Object Pete
Pete is a character associated with John Thornton, likely serving as his companion during travels or adventures.
E1364274 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: Pete | Statement: [John Thornton, travelsWith, Pete]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pete
Context triple: [John Thornton, travelsWith, Pete]
  • A. Pete
    Pete is the nickname of Grover Cleveland Alexander, a Hall of Fame Major League Baseball pitcher and one of the greatest hurlers of the early 20th century.
  • B. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • C. Pete
    Pete is the young orphaned boy who befriends and is protected by a friendly dragon in the Disney film "Pete's Dragon."
  • D. Pete
    Pete is a character in the 2014 found-footage-style disaster film "Into the Storm," which centers on a series of devastating tornadoes striking a small town.
  • E. Pete
    Pete is the nickname of Pete Vuckovich, a former Major League Baseball pitcher best known for winning the 1982 American League Cy Young Award with the Milwaukee Brewers.
  • 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: Pete
Triple: [John Thornton, travelsWith, Pete]
Generated description
Pete is a character associated with John Thornton, likely serving as his companion during travels or adventures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pete
Target entity description: Pete is a character associated with John Thornton, likely serving as his companion during travels or adventures.
  • A. Pete
    Pete is a supporting character in the comedy film "Knocked Up," portrayed as the somewhat immature yet well-meaning husband of Debbie and friend of the protagonist.
  • B. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • C. Pete
    Pete is a central figure in Stephen Crane’s novella "Maggie: A Girl of the Streets," representing the rough, working-class masculinity of New York’s Bowery slums.
  • D. Pete
    Pete is a common masculine given name, typically used as a familiar or informal form of the name Peter.
  • E. Pete
    Pete is the well-known nickname of Confederate General James Longstreet, one of Robert E. Lee’s principal corps commanders during the American Civil War.
  • 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_69d8e8cb8c348190b52075823911c869 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5f99d8ad0819098ebd4ee007149f1 completed April 20, 2026, 10:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0700e0a45c81909ff542041cf0626d completed May 15, 2026, 11:17 a.m.
NEDg Description generation batch_6a0701b45878819090790895e37bdaca completed May 15, 2026, 11:21 a.m.
NED2 Entity disambiguation (via description) batch_6a07022bed5c81909bfbad71467c9aa2 completed May 15, 2026, 11:23 a.m.
Created at: April 10, 2026, 1:19 p.m.