Triple

T9402832
Position Surface form Disambiguated ID Type / Status
Subject Roland Fryer E226516 entity
Predicate founded P104 FINISHED
Object Education Innovation Laboratory at Harvard University
The Education Innovation Laboratory at Harvard University is a research center that designs and evaluates data-driven strategies to improve educational outcomes, particularly for disadvantaged students.
E795874 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: Education Innovation Laboratory at Harvard University | Statement: [Roland Fryer, founded, Education Innovation Laboratory at Harvard University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Education Innovation Laboratory at Harvard University
Context triple: [Roland Fryer, founded, Education Innovation Laboratory at Harvard University]
  • A. Harvard Innovation Labs (in collaboration with Harvard University)
    Harvard Innovation Labs is a Harvard University-wide innovation and entrepreneurship ecosystem that provides students, alumni, and faculty with resources, mentorship, and space to develop and launch ventures across disciplines.
  • B. Office of Digital Learning at MIT
    The Office of Digital Learning at MIT is the institute’s central unit for developing, supporting, and advancing MIT’s online and technology-enabled education initiatives, including massive open online courses (MOOCs).
  • C. MIT Media Lab
    The MIT Media Lab is an interdisciplinary research laboratory at the Massachusetts Institute of Technology known for pioneering work at the intersection of technology, design, media, and human-computer interaction.
  • D. Centers of Innovation program
    The Centers of Innovation program is a Georgia state initiative that provides industry-focused research, technical expertise, and business support to help companies innovate and grow in key economic sectors.
  • E. Harvard John A. Paulson School of Engineering and Applied Sciences
    The Harvard John A. Paulson School of Engineering and Applied Sciences is Harvard University's engineering and applied sciences school, known for interdisciplinary research and education at the intersection of technology, science, and society.
  • 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: Education Innovation Laboratory at Harvard University
Triple: [Roland Fryer, founded, Education Innovation Laboratory at Harvard University]
Generated description
The Education Innovation Laboratory at Harvard University is a research center that designs and evaluates data-driven strategies to improve educational outcomes, particularly for disadvantaged students.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Education Innovation Laboratory at Harvard University
Target entity description: The Education Innovation Laboratory at Harvard University is a research center that designs and evaluates data-driven strategies to improve educational outcomes, particularly for disadvantaged students.
  • A. Harvard Innovation Labs (in collaboration with Harvard University)
    Harvard Innovation Labs is a Harvard University-wide innovation and entrepreneurship ecosystem that provides students, alumni, and faculty with resources, mentorship, and space to develop and launch ventures across disciplines.
  • B. Office of Digital Learning at MIT
    The Office of Digital Learning at MIT is the institute’s central unit for developing, supporting, and advancing MIT’s online and technology-enabled education initiatives, including massive open online courses (MOOCs).
  • C. MIT Media Lab
    The MIT Media Lab is an interdisciplinary research laboratory at the Massachusetts Institute of Technology known for pioneering work at the intersection of technology, design, media, and human-computer interaction.
  • D. Centers of Innovation program
    The Centers of Innovation program is a Georgia state initiative that provides industry-focused research, technical expertise, and business support to help companies innovate and grow in key economic sectors.
  • E. Harvard John A. Paulson School of Engineering and Applied Sciences
    The Harvard John A. Paulson School of Engineering and Applied Sciences is Harvard University's engineering and applied sciences school, known for interdisciplinary research and education at the intersection of technology, science, and society.
  • 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_69ca843170f88190800a8ab2b5fc568e completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd51be35cc8190bafad423a142c305 completed April 1, 2026, 5:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1012ca6c0819098c427233d226dd2 completed April 4, 2026, 12:16 p.m.
NEDg Description generation batch_69d101bf84548190a28e5f24aff265b1 completed April 4, 2026, 12:19 p.m.
NED2 Entity disambiguation (via description) batch_69d1025ebf5c8190914b682117b01827 completed April 4, 2026, 12:21 p.m.
Created at: March 30, 2026, 7:46 p.m.