Triple
T93493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard T.H. Chan School of Public Health |
E1878
|
entity |
| Predicate | hasDepartment |
P35
|
FINISHED |
| Object |
Department of Environmental Health
The Department of Environmental Health is an academic department at the Harvard T.H. Chan School of Public Health that focuses on how environmental and occupational exposures affect human health and on developing strategies to prevent related diseases.
|
E7937
|
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: Department of Environmental Health | Statement: [Harvard T.H. Chan School of Public Health, hasDepartment, Department of Environmental Health]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Department of Environmental Health Context triple: [Harvard T.H. Chan School of Public Health, hasDepartment, Department of Environmental Health]
-
A.
School of Public Health
The School of Public Health at the University of California, Berkeley is a leading institution dedicated to research, education, and practice in public health disciplines such as epidemiology, environmental health, health policy, and global health.
-
B.
United States Environmental Protection Agency
The United States Environmental Protection Agency is a federal government agency responsible for protecting human health and the environment through regulation, enforcement, and environmental research in the United States.
-
C.
Environment and Natural Resources Division
The Environment and Natural Resources Division is the branch of the U.S. Department of Justice responsible for enforcing federal environmental and natural resource laws and representing the United States in related litigation.
-
D.
Massachusetts Department of Public Health
The Massachusetts Department of Public Health is the state agency responsible for protecting and promoting public health in Massachusetts through disease prevention, health regulation, and community health programs.
-
E.
Council on Environmental Quality
The Council on Environmental Quality is a U.S. federal agency that coordinates environmental efforts across the executive branch and oversees implementation of the National Environmental Policy Act.
- 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: Department of Environmental Health Triple: [Harvard T.H. Chan School of Public Health, hasDepartment, Department of Environmental Health]
Generated description
The Department of Environmental Health is an academic department at the Harvard T.H. Chan School of Public Health that focuses on how environmental and occupational exposures affect human health and on developing strategies to prevent related diseases.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Department of Environmental Health Target entity description: The Department of Environmental Health is an academic department at the Harvard T.H. Chan School of Public Health that focuses on how environmental and occupational exposures affect human health and on developing strategies to prevent related diseases.
-
A.
School of Public Health
The School of Public Health at the University of California, Berkeley is a leading institution dedicated to research, education, and practice in public health disciplines such as epidemiology, environmental health, health policy, and global health.
-
B.
United States Environmental Protection Agency
The United States Environmental Protection Agency is a federal government agency responsible for protecting human health and the environment through regulation, enforcement, and environmental research in the United States.
-
C.
Environment and Natural Resources Division
The Environment and Natural Resources Division is the branch of the U.S. Department of Justice responsible for enforcing federal environmental and natural resource laws and representing the United States in related litigation.
-
D.
Massachusetts Department of Public Health
The Massachusetts Department of Public Health is the state agency responsible for protecting and promoting public health in Massachusetts through disease prevention, health regulation, and community health programs.
-
E.
Council on Environmental Quality
The Council on Environmental Quality is a U.S. federal agency that coordinates environmental efforts across the executive branch and oversees implementation of the National Environmental Policy Act.
- 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_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a24fd28e988190bde699647ee5b16b |
completed | Feb. 28, 2026, 2:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a26245bf748190828d5cb4624b2a79 |
completed | Feb. 28, 2026, 3:34 a.m. |
| NEDg | Description generation | batch_69a262bec71481909b251923011ca502 |
completed | Feb. 28, 2026, 3:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a263626b7c8190b53469d93ac604d9 |
completed | Feb. 28, 2026, 3:39 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.