Triple

T93437
Position Surface form Disambiguated ID Type / Status
Subject Harvard Kennedy School E1877 entity
Predicate hasDivision P35 FINISHED
Object Taubman Center for State and Local Government
The Taubman Center for State and Local Government is a research and policy center at Harvard Kennedy School focused on improving governance, management, and policy innovation in state and local governments.
E10320 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: Taubman Center for State and Local Government | Statement: [Harvard Kennedy School, hasDivision, Taubman Center for State and Local Government]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taubman Center for State and Local Government
Context triple: [Harvard Kennedy School, hasDivision, Taubman Center for State and Local Government]
  • A. Leventhal Center for Advanced Urbanism
    The Leventhal Center for Advanced Urbanism is an MIT research hub focused on innovative, interdisciplinary approaches to contemporary urban design, planning, and policy challenges.
  • B. University City Science Center
    The University City Science Center is a prominent urban research and technology innovation hub in Philadelphia that supports startups, academic partnerships, and commercialization of scientific advances.
  • C. John A. Wilson Building
    The John A. Wilson Building is a historic government office building in Washington, D.C., that houses the city’s primary municipal and legislative offices.
  • D. Wexner Learning Center
    The Wexner Learning Center is an educational facility within the United States Holocaust Memorial Museum that provides interactive resources and programs for studying the history and legacy of the Holocaust.
  • E. National Academy of Sciences Building
    The National Academy of Sciences Building is a historic Beaux-Arts landmark in Washington, D.C., serving as the headquarters and principal meeting place of the National Academy of Sciences.
  • 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: Taubman Center for State and Local Government
Triple: [Harvard Kennedy School, hasDivision, Taubman Center for State and Local Government]
Generated description
The Taubman Center for State and Local Government is a research and policy center at Harvard Kennedy School focused on improving governance, management, and policy innovation in state and local governments.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taubman Center for State and Local Government
Target entity description: The Taubman Center for State and Local Government is a research and policy center at Harvard Kennedy School focused on improving governance, management, and policy innovation in state and local governments.
  • A. Leventhal Center for Advanced Urbanism
    The Leventhal Center for Advanced Urbanism is an MIT research hub focused on innovative, interdisciplinary approaches to contemporary urban design, planning, and policy challenges.
  • B. University City Science Center
    The University City Science Center is a prominent urban research and technology innovation hub in Philadelphia that supports startups, academic partnerships, and commercialization of scientific advances.
  • C. John A. Wilson Building
    The John A. Wilson Building is a historic government office building in Washington, D.C., that houses the city’s primary municipal and legislative offices.
  • D. Wexner Learning Center
    The Wexner Learning Center is an educational facility within the United States Holocaust Memorial Museum that provides interactive resources and programs for studying the history and legacy of the Holocaust.
  • E. National Academy of Sciences Building
    The National Academy of Sciences Building is a historic Beaux-Arts landmark in Washington, D.C., serving as the headquarters and principal meeting place of the National Academy of Sciences.
  • 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_69a24d1a97dc819094e6c021fe9b05a7 completed Feb. 28, 2026, 2:04 a.m.
NER Named-entity recognition batch_69a24fd28e988190bde699647ee5b16b completed Feb. 28, 2026, 2:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69a26c1cdad88190aae17fcf5554a674 completed Feb. 28, 2026, 4:16 a.m.
NEDg Description generation batch_69a26f619a608190b9698811313a2b30 completed Feb. 28, 2026, 4:30 a.m.
NED2 Entity disambiguation (via description) batch_69a274ab28dc8190ba71579885e62994 completed Feb. 28, 2026, 4:52 a.m.
Created at: Feb. 28, 2026, 2:07 a.m.