Triple
T3833543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VX |
E91072
|
entity |
| Predicate | onsetOfSymptoms |
P9036
|
FINISHED |
| Object | seconds to minutes after exposure |
—
|
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: seconds to minutes after exposure | Statement: [VX, onsetOfSymptoms, seconds to minutes after exposure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onsetOfSymptoms Context triple: [VX, onsetOfSymptoms, seconds to minutes after exposure]
-
A.
hasOnset
chosen
Indicates the point in time or condition at which a process, event, or state begins.
-
B.
durationOfAffliction
Indicates the length of time that an affliction or condition persists for an entity.
-
C.
typicalOnsetLocation
Indicates the anatomical location where a condition, symptom, or process most commonly begins or first appears.
-
D.
symptom
Indicates that a particular condition, disease, or problem manifests through a specific observable sign or complaint.
-
E.
hasOnsetTypes
Indicates the types or categories of onset (e.g., how or when something begins) that are associated with a given entity or condition.
- 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_69aed960b538819096561c8ed448dec9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb88b8a8819082d4bdbc5bc45366 |
completed | March 9, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69aee74c2e04819094b94b3c0bac1806 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:17 p.m.