Triple
T903719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NOVA University Lisbon |
E19500
|
entity |
| Predicate | hasFaculty |
P141
|
FINISHED |
| Object |
NOVA National School of Public Health
NOVA National School of Public Health is a specialized public health higher education and research institution within NOVA University Lisbon, focused on training professionals and advancing knowledge in population health, health policy, and health systems.
|
E106464
|
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: NOVA National School of Public Health | Statement: [NOVA University Lisbon, hasFaculty, NOVA National School of Public Health]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NOVA National School of Public Health Context triple: [NOVA University Lisbon, hasFaculty, NOVA National School of Public Health]
-
A.
Harvard T.H. Chan School of Public Health
Harvard T.H. Chan School of Public Health is a leading graduate institution dedicated to advancing public health through research, education, and policy, and is part of Harvard University.
-
B.
Mailman School of Public Health
The Mailman School of Public Health is Columbia University's graduate school dedicated to public health education, research, and policy.
-
C.
NOVA Medical School
NOVA Medical School is the medical faculty of NOVA University Lisbon, known for its research-driven education in medicine and health sciences in Portugal.
-
D.
Milken Institute School of Public Health
The Milken Institute School of Public Health is George Washington University’s public health school, known for its programs and research in global health, health policy, and population health.
-
E.
NOVA School of Social Sciences and Humanities
NOVA School of Social Sciences and Humanities is a faculty of NOVA University Lisbon specializing in education and research across the social sciences, arts, and humanities.
- 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: NOVA National School of Public Health Triple: [NOVA University Lisbon, hasFaculty, NOVA National School of Public Health]
Generated description
NOVA National School of Public Health is a specialized public health higher education and research institution within NOVA University Lisbon, focused on training professionals and advancing knowledge in population health, health policy, and health systems.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: NOVA National School of Public Health Target entity description: NOVA National School of Public Health is a specialized public health higher education and research institution within NOVA University Lisbon, focused on training professionals and advancing knowledge in population health, health policy, and health systems.
-
A.
Harvard T.H. Chan School of Public Health
Harvard T.H. Chan School of Public Health is a leading graduate institution dedicated to advancing public health through research, education, and policy, and is part of Harvard University.
-
B.
Mailman School of Public Health
The Mailman School of Public Health is Columbia University's graduate school dedicated to public health education, research, and policy.
-
C.
NOVA Medical School
chosen
NOVA Medical School is the medical faculty of NOVA University Lisbon, known for its research-driven education in medicine and health sciences in Portugal.
-
D.
Milken Institute School of Public Health
The Milken Institute School of Public Health is George Washington University’s public health school, known for its programs and research in global health, health policy, and population health.
-
E.
NOVA School of Social Sciences and Humanities
NOVA School of Social Sciences and Humanities is a faculty of NOVA University Lisbon specializing in education and research across the social sciences, arts, and humanities.
- 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_69a4939e889c8190ac148b3ac1a7f90b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad58334881908df191140b786780 |
completed | March 1, 2026, 9:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7cf5a4118819086035d6e250a53cc |
completed | March 4, 2026, 6:21 a.m. |
| NEDg | Description generation | batch_69a7d082b4388190bcf04692c273e5cc |
completed | March 4, 2026, 6:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a7d49784d08190b334de4fe634f1c6 |
completed | March 4, 2026, 6:43 a.m. |
Created at: March 1, 2026, 7:39 p.m.