Triple

T1512609
Position Surface form Disambiguated ID Type / Status
Subject Georgia Institute of Technology E32046 entity
Predicate mascot P52 FINISHED
Object Buzz
Buzz is the yellow jacket costumed mascot of the Georgia Institute of Technology, known for energizing crowds at the university’s athletic and campus events.
 E172176 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: Buzz | Statement: [Georgia Institute of Technology, mascot, Buzz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Buzz
Context triple: [Georgia Institute of Technology, mascot, Buzz]
  • A. Buzz
    Buzz is the nickname of Edwin "Buzz" Aldrin, the American astronaut who became the second person to walk on the Moon during the Apollo 11 mission.
  • B. BZZ
    BZZ is the IATA airport code for RAF Brize Norton, a major Royal Air Force transport and air-to-air refuelling base in Oxfordshire, England.
  • C. BZ
    BZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Belize.
  • D. BAT
    BAT is a major multinational tobacco company known for producing and marketing cigarettes and other nicotine products worldwide.
  • E. Bou
    Bou is a surname of Spanish origin borne by Argentine professional footballer Gustavo Bou, among others.
  • 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: Buzz
Triple: [Georgia Institute of Technology, mascot, Buzz]
Generated description
Buzz is the yellow jacket costumed mascot of the Georgia Institute of Technology, known for energizing crowds at the university’s athletic and campus events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Buzz
Target entity description: Buzz is the yellow jacket costumed mascot of the Georgia Institute of Technology, known for energizing crowds at the university’s athletic and campus events.
  • A. Buzz
    Buzz is the nickname of Edwin "Buzz" Aldrin, the American astronaut who became the second person to walk on the Moon during the Apollo 11 mission.
  • B. BZZ
    BZZ is the IATA airport code for RAF Brize Norton, a major Royal Air Force transport and air-to-air refuelling base in Oxfordshire, England.
  • C. BZ
    BZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Belize.
  • D. BAT
    BAT is a major multinational tobacco company known for producing and marketing cigarettes and other nicotine products worldwide.
  • E. Bou
    Bou is a surname of Spanish origin borne by Argentine professional footballer Gustavo Bou, among others.
  • 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_69a885e8caf88190a5fbb6159ce87786 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a907d7cbf48190be40590a7f9fa1de completed March 5, 2026, 4:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad23409fd481909834aaf0dc4641f6 completed March 8, 2026, 7:20 a.m.
NEDg Description generation batch_69ad23b8d570819099b953c7a60e9445 completed March 8, 2026, 7:22 a.m.
NED2 Entity disambiguation (via description) batch_69ad248193ec8190b0c08ef979661af0 completed March 8, 2026, 7:25 a.m.
Created at: March 4, 2026, 7:26 p.m.