Triple
T28818234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epstein–Barr virus infection |
E727688
|
entity |
| Predicate | higherRiskGroup |
P161408
|
FINISHED |
| Object | immunocompromised patients |
—
|
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: immunocompromised patients | Statement: [Epstein–Barr virus infection, higherRiskGroup, immunocompromised patients]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: higherRiskGroup Context triple: [Epstein–Barr virus infection, higherRiskGroup, immunocompromised patients]
-
A.
hasRiskFactorFor
Indicates that one entity contributes to or increases the likelihood of another entity experiencing a particular risk or adverse outcome.
-
B.
riskIfTooHigh
Indicates that a certain level or value becomes risky or dangerous when it exceeds a specified threshold.
-
C.
hasRiskFrom
Indicates that one entity is exposed to or may suffer potential harm, loss, or adverse effects as a result of another entity.
-
D.
vulnerableGroup
chosen
Indicates that the referenced group is at increased risk of harm, disadvantage, or negative outcomes compared to others.
-
E.
hasRiskStatus
Indicates the level or category of risk currently associated with an 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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f71422adac8190a5ceb32dcf820833 |
completed | May 3, 2026, 9:23 a.m. |
| PD | Predicate disambiguation | batch_69f712764d2c819081b64b27e5de4a13 |
completed | May 3, 2026, 9:16 a.m. |
Created at: April 28, 2026, 6:33 a.m.