Triple

T609162
Position Surface form Disambiguated ID Type / Status
Subject Boston University E12058 entity
Predicate athleticsNickname P55 FINISHED
Object Terriers
The Terriers are the athletic teams representing Boston University in collegiate sports competitions.
E76302 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: Terriers | Statement: [Boston University, athleticsNickname, Terriers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terriers
Context triple: [Boston University, athleticsNickname, Terriers]
  • A. Chester French
    Chester French is an American indie pop duo known for their genre-blending sound, witty lyrics, and early association with producers like Pharrell Williams.
  • B. Bulldogs
    Bulldogs is the nickname of Yale University's men's basketball team, a historic Ivy League program competing in NCAA Division I.
  • C. Labrador
    Labrador is a vast, sparsely populated region in eastern Canada known for its rugged subarctic landscapes, rich mineral resources, and Indigenous Inuit and Innu communities.
  • D. Chihuahua
    Chihuahua is Mexico’s largest state by area, known for its desert landscapes, rugged mountain ranges, and significant role in the country’s history and industry.
  • E. Greyhound
    Greyhound is a 2020 World War II naval thriller film starring Tom Hanks as a U.S. destroyer captain escorting Allied convoys across the Atlantic while evading German U-boats.
  • 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: Terriers
Triple: [Boston University, athleticsNickname, Terriers]
Generated description
The Terriers are the athletic teams representing Boston University in collegiate sports competitions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terriers
Target entity description: The Terriers are the athletic teams representing Boston University in collegiate sports competitions.
  • A. Chester French
    Chester French is an American indie pop duo known for their genre-blending sound, witty lyrics, and early association with producers like Pharrell Williams.
  • B. Bulldogs
    Bulldogs is the nickname of Yale University's men's basketball team, a historic Ivy League program competing in NCAA Division I.
  • C. Labrador
    Labrador is a vast, sparsely populated region in eastern Canada known for its rugged subarctic landscapes, rich mineral resources, and Indigenous Inuit and Innu communities.
  • D. Chihuahua
    Chihuahua is Mexico’s largest state by area, known for its desert landscapes, rugged mountain ranges, and significant role in the country’s history and industry.
  • E. Greyhound
    Greyhound is a 2020 World War II naval thriller film starring Tom Hanks as a U.S. destroyer captain escorting Allied convoys across the Atlantic while evading German U-boats.
  • 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_69a493309df48190a327f748e88049a6 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49df54eec8190af3f5f04c01d5d2a completed March 1, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69a52eacec94819094e920ab1c0659e8 completed March 2, 2026, 6:31 a.m.
NEDg Description generation batch_69a53062c138819095262b45396fc97a completed March 2, 2026, 6:38 a.m.
NED2 Entity disambiguation (via description) batch_69a530f8c6b08190b987016e8e8c11b6 completed March 2, 2026, 6:40 a.m.
Created at: March 1, 2026, 7:35 p.m.