Triple
T362153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surgeon General’s Report on Smoking and Health |
E7878
|
entity |
| Predicate | preparedBy |
P2210
|
FINISHED |
| Object |
Advisory Committee to the Surgeon General of the United States
The Advisory Committee to the Surgeon General of the United States was a panel of medical and scientific experts convened to evaluate evidence on the health effects of smoking and inform landmark federal public health guidance.
|
E46639
|
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: Advisory Committee to the Surgeon General of the United States | Statement: [Surgeon General’s Report on Smoking and Health, preparedBy, Advisory Committee to the Surgeon General of the United States]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Advisory Committee to the Surgeon General of the United States Context triple: [Surgeon General’s Report on Smoking and Health, preparedBy, Advisory Committee to the Surgeon General of the United States]
-
A.
Office of the Surgeon General
The Office of the Surgeon General is the federal public health leadership office in the United States that supports the Surgeon General in providing national health guidance, policy recommendations, and oversight of public health initiatives.
-
B.
National Academies of Sciences, Engineering, and Medicine
The National Academies of Sciences, Engineering, and Medicine is a collective advisory organization in the United States that provides independent, evidence-based guidance on scientific, engineering, and medical issues to policymakers and the public.
-
C.
National Academy of Medicine
The National Academy of Medicine is a leading U.S. nonprofit institution that provides expert, evidence-based advice on health, medicine, and biomedical science to inform policy and improve public health.
-
D.
United States Department of Health and Human Services
The United States Department of Health and Human Services is a federal executive department responsible for protecting the health of Americans and providing essential human services, particularly for those least able to help themselves.
-
E.
National Institutes of Health
The National Institutes of Health is the United States’ primary federal biomedical research agency, supporting and conducting medical research to improve public health.
- 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: Advisory Committee to the Surgeon General of the United States Triple: [Surgeon General’s Report on Smoking and Health, preparedBy, Advisory Committee to the Surgeon General of the United States]
Generated description
The Advisory Committee to the Surgeon General of the United States was a panel of medical and scientific experts convened to evaluate evidence on the health effects of smoking and inform landmark federal public health guidance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Advisory Committee to the Surgeon General of the United States Target entity description: The Advisory Committee to the Surgeon General of the United States was a panel of medical and scientific experts convened to evaluate evidence on the health effects of smoking and inform landmark federal public health guidance.
-
A.
Office of the Surgeon General
The Office of the Surgeon General is the federal public health leadership office in the United States that supports the Surgeon General in providing national health guidance, policy recommendations, and oversight of public health initiatives.
-
B.
National Academies of Sciences, Engineering, and Medicine
The National Academies of Sciences, Engineering, and Medicine is a collective advisory organization in the United States that provides independent, evidence-based guidance on scientific, engineering, and medical issues to policymakers and the public.
-
C.
National Academy of Medicine
The National Academy of Medicine is a leading U.S. nonprofit institution that provides expert, evidence-based advice on health, medicine, and biomedical science to inform policy and improve public health.
-
D.
United States Department of Health and Human Services
The United States Department of Health and Human Services is a federal executive department responsible for protecting the health of Americans and providing essential human services, particularly for those least able to help themselves.
-
E.
National Institutes of Health
The National Institutes of Health is the United States’ primary federal biomedical research agency, supporting and conducting medical research to improve public health.
- 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_69a2e7e880008190a6ad7e06e5d03007 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ebcfb0f48190b9a9010c7837ac58 |
completed | Feb. 28, 2026, 1:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3eca750748190b5a2914f318bc1c2 |
completed | March 1, 2026, 7:37 a.m. |
| NEDg | Description generation | batch_69a3ed7d472c8190afd508fcb71c93c7 |
completed | March 1, 2026, 7:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a3edd107e08190ad7107ce9f6996ba |
completed | March 1, 2026, 7:42 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.