Triple

T338450
Position Surface form Disambiguated ID Type / Status
Subject Columbia University Graduate School of Journalism E6779 entity
Predicate hasResearchCenter P40 FINISHED
Object Brown Institute for Media Innovation
The Brown Institute for Media Innovation is a research center that supports cutting-edge projects at the intersection of journalism, technology, and storytelling.
E43493 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: Brown Institute for Media Innovation | Statement: [Columbia University Graduate School of Journalism, hasResearchCenter, Brown Institute for Media Innovation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brown Institute for Media Innovation
Context triple: [Columbia University Graduate School of Journalism, hasResearchCenter, Brown Institute for Media Innovation]
  • A. Tow Center for Digital Journalism
    The Tow Center for Digital Journalism is a research institute at Columbia University that explores the impact of technology on journalism and develops innovative practices for digital news production.
  • B. Columbia University Graduate School of Journalism
    Columbia University Graduate School of Journalism is a leading graduate institution in New York City renowned for training professional journalists and advancing excellence in the field through education, research, and industry partnerships.
  • C. Annenberg School for Communication
    The Annenberg School for Communication is a leading academic institution specializing in communication research and education, renowned for its scholarship in media, politics, and public policy.
  • D. Schwarzman College of Computing
    Schwarzman College of Computing is MIT’s interdisciplinary hub for computer science, artificial intelligence, and computing-related research and education across the institute.
  • E. Rappaport Institute for Greater Boston
    The Rappaport Institute for Greater Boston is a Harvard Kennedy School research and policy center focused on improving governance and quality of life in the Greater Boston region through research, public service, and civic engagement.
  • 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: Brown Institute for Media Innovation
Triple: [Columbia University Graduate School of Journalism, hasResearchCenter, Brown Institute for Media Innovation]
Generated description
The Brown Institute for Media Innovation is a research center that supports cutting-edge projects at the intersection of journalism, technology, and storytelling.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brown Institute for Media Innovation
Target entity description: The Brown Institute for Media Innovation is a research center that supports cutting-edge projects at the intersection of journalism, technology, and storytelling.
  • A. Tow Center for Digital Journalism
    The Tow Center for Digital Journalism is a research institute at Columbia University that explores the impact of technology on journalism and develops innovative practices for digital news production.
  • B. Columbia University Graduate School of Journalism
    Columbia University Graduate School of Journalism is a leading graduate institution in New York City renowned for training professional journalists and advancing excellence in the field through education, research, and industry partnerships.
  • C. Annenberg School for Communication
    The Annenberg School for Communication is a leading academic institution specializing in communication research and education, renowned for its scholarship in media, politics, and public policy.
  • D. Schwarzman College of Computing
    Schwarzman College of Computing is MIT’s interdisciplinary hub for computer science, artificial intelligence, and computing-related research and education across the institute.
  • E. Rappaport Institute for Greater Boston
    The Rappaport Institute for Greater Boston is a Harvard Kennedy School research and policy center focused on improving governance and quality of life in the Greater Boston region through research, public service, and civic engagement.
  • 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_69a2e79434908190a9d5afe415153ad9 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2eae23b0c819081f8bf9ac26685ab completed Feb. 28, 2026, 1:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3d4e56b448190aac66218417e95b8 completed March 1, 2026, 5:55 a.m.
NEDg Description generation batch_69a3d53d4b788190936b3c5f92877c8d completed March 1, 2026, 5:57 a.m.
NED2 Entity disambiguation (via description) batch_69a3d602aa6881908fbdb4c25e8f8cb5 completed March 1, 2026, 6 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.