Triple
T13620364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Baltimore |
E325432
|
entity |
| Predicate | researchFocus |
P31
|
FINISHED |
| Object |
RNA tumor viruses
RNA tumor viruses are a class of retroviruses that use RNA as their genetic material and can induce cancer by integrating into host cell genomes and disrupting normal cellular regulation.
|
E1051819
|
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: RNA tumor viruses | Statement: [David Baltimore, researchFocus, RNA tumor viruses]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RNA tumor viruses Context triple: [David Baltimore, researchFocus, RNA tumor viruses]
-
A.
Molecular Biology of Bacterial Viruses
Molecular Biology of Bacterial Viruses is a classic scientific monograph that helped establish the foundations of molecular genetics through the study of bacteriophages.
-
B.
Principles of Virology
Principles of Virology is a foundational textbook that systematically explains the molecular biology, pathogenesis, and epidemiology of viruses and viral diseases.
-
C.
Arenaviruses
Arenaviruses are a family of enveloped RNA viruses that primarily infect rodents and can cause severe hemorrhagic fevers in humans, such as Lassa fever, making them significant public health threats.
-
D.
Mastadenovirus
Mastadenovirus is a genus of non-enveloped, double-stranded DNA viruses in the Adenoviridae family that infect mammals, including humans, and are associated with a range of respiratory, ocular, and gastrointestinal diseases.
-
E.
bacteriophage T1
Bacteriophage T1 is a virulent E. coli-infecting virus historically important in genetics for studies of mutation and bacterial resistance.
- 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: RNA tumor viruses Triple: [David Baltimore, researchFocus, RNA tumor viruses]
Generated description
RNA tumor viruses are a class of retroviruses that use RNA as their genetic material and can induce cancer by integrating into host cell genomes and disrupting normal cellular regulation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: RNA tumor viruses Target entity description: RNA tumor viruses are a class of retroviruses that use RNA as their genetic material and can induce cancer by integrating into host cell genomes and disrupting normal cellular regulation.
-
A.
Molecular Biology of Bacterial Viruses
Molecular Biology of Bacterial Viruses is a classic scientific monograph that helped establish the foundations of molecular genetics through the study of bacteriophages.
-
B.
Principles of Virology
Principles of Virology is a foundational textbook that systematically explains the molecular biology, pathogenesis, and epidemiology of viruses and viral diseases.
-
C.
Arenaviruses
Arenaviruses are a family of enveloped RNA viruses that primarily infect rodents and can cause severe hemorrhagic fevers in humans, such as Lassa fever, making them significant public health threats.
-
D.
Mastadenovirus
Mastadenovirus is a genus of non-enveloped, double-stranded DNA viruses in the Adenoviridae family that infect mammals, including humans, and are associated with a range of respiratory, ocular, and gastrointestinal diseases.
-
E.
bacteriophage T1
Bacteriophage T1 is a virulent E. coli-infecting virus historically important in genetics for studies of mutation and bacterial resistance.
- 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_69d8076aae28819092cf636190ee5529 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb0b0c9008190836242da2d6a8cbe |
completed | April 12, 2026, 2:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f77fa0b81c819094e2fa209ef9857c |
completed | May 3, 2026, 5:02 p.m. |
| NEDg | Description generation | batch_69f783c24d088190ad53fa2d33a255c9 |
completed | May 3, 2026, 5:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f78452e8bc8190a55f2be349fe718f |
completed | May 3, 2026, 5:22 p.m. |
Created at: April 9, 2026, 9:50 p.m.