Triple
T2389286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ann Dowling |
E48901
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Dowling Review of Business–University Research Collaborations
The Dowling Review of Business–University Research Collaborations is an influential report led by engineer Ann Dowling that examines how to strengthen partnerships between UK businesses and universities to drive innovation and economic growth.
|
E261944
|
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: Dowling Review of Business–University Research Collaborations | Statement: [Ann Dowling, notableWork, Dowling Review of Business–University Research Collaborations]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dowling Review of Business–University Research Collaborations Context triple: [Ann Dowling, notableWork, Dowling Review of Business–University Research Collaborations]
-
A.
Technical Corrections to the Bayh–Dole Act
Technical Corrections to the Bayh–Dole Act is a legislative measure that refined and clarified the original Bayh–Dole Act’s provisions governing the ownership and commercialization of inventions arising from federally funded research.
-
B.
Knowledge and Innovation Communities
Knowledge and Innovation Communities are large-scale, EU-backed partnerships that bring together businesses, research institutions, and universities to drive innovation, entrepreneurship, and education in specific thematic areas.
-
C.
Associated Countries to the European Research Area
Associated Countries to the European Research Area are non-EU states that participate in the EU’s research and innovation framework programs under similar conditions to member countries, fostering integrated scientific collaboration across Europe.
-
D.
Science and Engineering Indicators report
The Science and Engineering Indicators report is a comprehensive, data-driven assessment of the state of U.S. and global science, technology, engineering, and mathematics (STEM) research, education, and innovation.
-
E.
Centre for Business Research
The Centre for Business Research is a research institute at the University of Cambridge that focuses on the study of enterprise, innovation, and economic performance, particularly in relation to policy and business practice.
- 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: Dowling Review of Business–University Research Collaborations Triple: [Ann Dowling, notableWork, Dowling Review of Business–University Research Collaborations]
Generated description
The Dowling Review of Business–University Research Collaborations is an influential report led by engineer Ann Dowling that examines how to strengthen partnerships between UK businesses and universities to drive innovation and economic growth.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dowling Review of Business–University Research Collaborations Target entity description: The Dowling Review of Business–University Research Collaborations is an influential report led by engineer Ann Dowling that examines how to strengthen partnerships between UK businesses and universities to drive innovation and economic growth.
-
A.
Technical Corrections to the Bayh–Dole Act
Technical Corrections to the Bayh–Dole Act is a legislative measure that refined and clarified the original Bayh–Dole Act’s provisions governing the ownership and commercialization of inventions arising from federally funded research.
-
B.
Knowledge and Innovation Communities
Knowledge and Innovation Communities are large-scale, EU-backed partnerships that bring together businesses, research institutions, and universities to drive innovation, entrepreneurship, and education in specific thematic areas.
-
C.
Associated Countries to the European Research Area
Associated Countries to the European Research Area are non-EU states that participate in the EU’s research and innovation framework programs under similar conditions to member countries, fostering integrated scientific collaboration across Europe.
-
D.
Science and Engineering Indicators report
The Science and Engineering Indicators report is a comprehensive, data-driven assessment of the state of U.S. and global science, technology, engineering, and mathematics (STEM) research, education, and innovation.
-
E.
Centre for Business Research
The Centre for Business Research is a research institute at the University of Cambridge that focuses on the study of enterprise, innovation, and economic performance, particularly in relation to policy and business practice.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7dca9248190b634ae9e02f6899a |
completed | March 7, 2026, 6:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3d2ad588190a2cf3adab6a9404d |
completed | March 9, 2026, 11:49 a.m. |
| NEDg | Description generation | batch_69aeb40b12d0819092b6c441580698a5 |
completed | March 9, 2026, 11:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69aeb471c0408190bfb2341899d44dba |
completed | March 9, 2026, 11:52 a.m. |
Created at: March 4, 2026, 7:57 p.m.