Triple

T5056687
Position Surface form Disambiguated ID Type / Status
Subject Tommy Dorsey E113919 entity
Predicate collaboratedWith P435 FINISHED
Object Sy Oliver
Sy Oliver was an influential American jazz arranger, trumpeter, and bandleader known for his innovative work with big bands in the swing era.
E490484 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: Sy Oliver | Statement: [Tommy Dorsey, collaboratedWith, Sy Oliver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sy Oliver
Context triple: [Tommy Dorsey, collaboratedWith, Sy Oliver]
  • A. Pete Olson
    Pete Olson is an American Republican politician who represented Texas's 22nd congressional district in the U.S. House of Representatives from 2009 to 2021.
  • B. Bryce Soderberg
    Bryce Soderberg is a Canadian musician best known as the bassist and backing vocalist for the American rock band Lifehouse.
  • C. Jake Evers
    Jake Evers is an individual known primarily as a notable bearer of the surname Evers.
  • D. Dustin O’Halloran
    Dustin O’Halloran is an American pianist and composer known for his emotive solo piano works and acclaimed film and television scores.
  • E. Oscar Martinez
    Oscar Martinez is a fictional accountant on the U.S. version of "The Office," known for his intelligence, dry wit, and often being the voice of reason among his eccentric coworkers.
  • 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: Sy Oliver
Triple: [Tommy Dorsey, collaboratedWith, Sy Oliver]
Generated description
Sy Oliver was an influential American jazz arranger, trumpeter, and bandleader known for his innovative work with big bands in the swing era.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sy Oliver
Target entity description: Sy Oliver was an influential American jazz arranger, trumpeter, and bandleader known for his innovative work with big bands in the swing era.
  • A. Pete Olson
    Pete Olson is an American Republican politician who represented Texas's 22nd congressional district in the U.S. House of Representatives from 2009 to 2021.
  • B. Bryce Soderberg
    Bryce Soderberg is a Canadian musician best known as the bassist and backing vocalist for the American rock band Lifehouse.
  • C. Jake Evers
    Jake Evers is an individual known primarily as a notable bearer of the surname Evers.
  • D. Dustin O’Halloran
    Dustin O’Halloran is an American pianist and composer known for his emotive solo piano works and acclaimed film and television scores.
  • E. Oscar Martinez
    Oscar Martinez is a fictional accountant on the U.S. version of "The Office," known for his intelligence, dry wit, and often being the voice of reason among his eccentric coworkers.
  • 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_69bd443aa1f88190abb992d138f2cf42 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7450312881908d4e3576ca65f7fb completed March 20, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea48cc7b88190a9ea43f79b0a0cf0 completed March 21, 2026, 2 p.m.
NEDg Description generation batch_69bea654fa8881908a50be410d4ea7d5 completed March 21, 2026, 2:08 p.m.
NED2 Entity disambiguation (via description) batch_69bea6ad303481909c41af9a4e002e0b completed March 21, 2026, 2:09 p.m.
Created at: March 20, 2026, 1:38 p.m.