Triple
T70156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | School of Computer Science, Carnegie Mellon University |
E1403
|
entity |
| Predicate | hasSubOrganization |
P747
|
FINISHED |
| Object |
Institute for Software Research, Carnegie Mellon University
The Institute for Software Research at Carnegie Mellon University is a leading academic center focused on research and education in software engineering, cybersecurity, privacy, and socio-technical systems.
|
E11681
|
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: Institute for Software Research, Carnegie Mellon University | Statement: [School of Computer Science, Carnegie Mellon University, hasSubOrganization, Institute for Software Research, Carnegie Mellon University]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Institute for Software Research, Carnegie Mellon University Context triple: [School of Computer Science, Carnegie Mellon University, hasSubOrganization, Institute for Software Research, Carnegie Mellon University]
-
A.
Computer Science Department, Carnegie Mellon University
The Computer Science Department at Carnegie Mellon University is a core academic unit renowned for pioneering research and education in computer science within CMU’s School of Computer Science.
-
B.
Human-Computer Interaction Institute, Carnegie Mellon University
The Human-Computer Interaction Institute at Carnegie Mellon University is a leading interdisciplinary research and education center focused on the design, study, and engineering of interactive computing systems and user experiences.
-
C.
Language Technologies Institute, Carnegie Mellon University
The Language Technologies Institute at Carnegie Mellon University is a leading research and education center focused on areas such as natural language processing, machine learning for language, speech recognition, and related AI-driven language technologies.
-
D.
Robotics Institute, Carnegie Mellon University
The Robotics Institute at Carnegie Mellon University is a leading research and education center dedicated to advancing the science and technology of robotics and artificial intelligence.
-
E.
Machine Learning Department, Carnegie Mellon University
The Machine Learning Department at Carnegie Mellon University is a pioneering academic unit dedicated to research and education in machine learning, artificial intelligence, and related computational 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: Institute for Software Research, Carnegie Mellon University Triple: [School of Computer Science, Carnegie Mellon University, hasSubOrganization, Institute for Software Research, Carnegie Mellon University]
Generated description
The Institute for Software Research at Carnegie Mellon University is a leading academic center focused on research and education in software engineering, cybersecurity, privacy, and socio-technical systems.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Institute for Software Research, Carnegie Mellon University Target entity description: The Institute for Software Research at Carnegie Mellon University is a leading academic center focused on research and education in software engineering, cybersecurity, privacy, and socio-technical systems.
-
A.
Computer Science Department, Carnegie Mellon University
The Computer Science Department at Carnegie Mellon University is a core academic unit renowned for pioneering research and education in computer science within CMU’s School of Computer Science.
-
B.
Human-Computer Interaction Institute, Carnegie Mellon University
The Human-Computer Interaction Institute at Carnegie Mellon University is a leading interdisciplinary research and education center focused on the design, study, and engineering of interactive computing systems and user experiences.
-
C.
Language Technologies Institute, Carnegie Mellon University
The Language Technologies Institute at Carnegie Mellon University is a leading research and education center focused on areas such as natural language processing, machine learning for language, speech recognition, and related AI-driven language technologies.
-
D.
Robotics Institute, Carnegie Mellon University
The Robotics Institute at Carnegie Mellon University is a leading research and education center dedicated to advancing the science and technology of robotics and artificial intelligence.
-
E.
Machine Learning Department, Carnegie Mellon University
The Machine Learning Department at Carnegie Mellon University is a pioneering academic unit dedicated to research and education in machine learning, artificial intelligence, and related computational disciplines.
- 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_69a24c06b3bc8190aa4ac89026115efc |
completed | Feb. 28, 2026, 1:59 a.m. |
| NER | Named-entity recognition | batch_69a24f045d38819088f5f71e39fa1ee7 |
completed | Feb. 28, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a27bff33b8819084f00ed115ebedeb |
completed | Feb. 28, 2026, 5:24 a.m. |
| NEDg | Description generation | batch_69a27f2f07d88190832000212142b088 |
completed | Feb. 28, 2026, 5:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a27ffd4818819091a276d54c750dc0 |
completed | Feb. 28, 2026, 5:41 a.m. |
Created at: Feb. 28, 2026, 2:03 a.m.