Triple
T1511203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MIT School of Architecture and Planning |
E32016
|
entity |
| Predicate | hasAcademicUnit |
P1488
|
FINISHED |
| Object |
MIT City Science group
The MIT City Science group is a research initiative within MIT that explores innovative urban design, data-driven planning, and new technologies to improve how cities function and how people live in them.
|
E465
|
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: MIT City Science group | Statement: [MIT School of Architecture and Planning, hasAcademicUnit, MIT City Science group]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MIT City Science group Context triple: [MIT School of Architecture and Planning, hasAcademicUnit, MIT City Science group]
-
A.
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.
-
B.
Mansueto Institute for Urban Innovation
The Mansueto Institute for Urban Innovation is a University of Chicago research hub dedicated to advancing data-driven, interdisciplinary solutions to complex urban challenges worldwide.
-
C.
DevTech Research Group
DevTech Research Group is an educational research lab at Tufts University focused on designing and studying innovative technologies and curricula that support young children’s learning and development, particularly in early computing and STEM.
-
D.
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.
-
E.
Harvard Center for Geographic Analysis
The Harvard Center for Geographic Analysis is a research hub at Harvard University that advances the use of geographic information systems (GIS) and spatial analysis across disciplines.
- 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: MIT City Science group Triple: [MIT School of Architecture and Planning, hasAcademicUnit, MIT City Science group]
Generated description
The MIT City Science group is a research initiative within MIT that explores innovative urban design, data-driven planning, and new technologies to improve how cities function and how people live in them.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MIT City Science group Target entity description: The MIT City Science group is a research initiative within MIT that explores innovative urban design, data-driven planning, and new technologies to improve how cities function and how people live in them.
-
A.
MIT Media Lab
chosen
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.
-
B.
Mansueto Institute for Urban Innovation
The Mansueto Institute for Urban Innovation is a University of Chicago research hub dedicated to advancing data-driven, interdisciplinary solutions to complex urban challenges worldwide.
-
C.
DevTech Research Group
DevTech Research Group is an educational research lab at Tufts University focused on designing and studying innovative technologies and curricula that support young children’s learning and development, particularly in early computing and STEM.
-
D.
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.
-
E.
Harvard Center for Geographic Analysis
The Harvard Center for Geographic Analysis is a research hub at Harvard University that advances the use of geographic information systems (GIS) and spatial analysis across disciplines.
- F. None of above.
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_69aa61db41c88190a2d97cc9cbbc3f06 |
completed | March 6, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad233e6e748190929b3f339cc9bd4b |
completed | March 8, 2026, 7:20 a.m. |
| NEDg | Description generation | batch_69ad23e279e88190ae341af34ea98487 |
completed | March 8, 2026, 7:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad24f7d8b081909241ab3995172f4d |
completed | March 8, 2026, 7:27 a.m. |
Created at: March 4, 2026, 7:26 p.m.