Triple
T21154220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIGA Technologies |
E521269
|
entity |
| Predicate | drugTargetPathogen |
P51612
|
FINISHED |
| Object | variola virus |
—
|
LITERAL FINISHED |
How this triple was built (2 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: variola virus | Statement: [SIGA Technologies, drugTargetPathogen, variola virus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drugTargetPathogen Context triple: [SIGA Technologies, drugTargetPathogen, variola virus]
-
A.
isPathogenOf
Indicates that one entity is a disease-causing agent (pathogen) that infects or causes illness in another entity.
-
B.
pathogenType
Indicates the specific kind or category of pathogen associated with or responsible for an entity or condition.
-
C.
addressesPathogen
chosen
Indicates that an action, intervention, or measure is directed toward counteracting, managing, or mitigating a specific pathogen.
-
D.
drugSusceptibility
Indicates that one entity (typically a microorganism, cell, or condition) is vulnerable or responsive to the effects of a specified drug or therapeutic agent.
-
E.
includesPathogensOf
Indicates that one entity contains or encompasses the pathogens that are associated with or originate from another entity.
- F. None of above.
Provenance (3 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_69e0b50d1ea481909c07e63c3ead9316 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7252a48788190bfdfe811fc6cfc06 |
completed | April 21, 2026, 7:20 a.m. |
| PD | Predicate disambiguation | batch_69e5f5f8a5bc819081918c7fa8e4496d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 2:58 p.m.