Triple
T22139329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | inyanga |
E547115
|
entity |
| Predicate | diagnosesBy |
P52059
|
FINISHED |
| Object | observation of symptoms |
—
|
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: observation of symptoms | Statement: [inyanga, diagnosesBy, observation of symptoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: diagnosesBy Context triple: [inyanga, diagnosesBy, observation of symptoms]
-
A.
diagnoses
Indicates that a medical professional identifies and determines the nature or cause of a condition, disease, or problem in a patient.
-
B.
diagnosedWith
Indicates that a subject has been identified, typically by a medical professional, as having a particular disease or medical condition.
-
C.
diagnosisMethod
chosen
Indicates the method, procedure, or technique used to establish or confirm a diagnosis for a condition or case.
-
D.
diagnosisDate
Indicates the date on which a diagnosis was formally established or recorded for an entity.
-
E.
hasDiagnosticFinding
Indicates that a subject (e.g., a patient, test, or examination) is associated with a specific diagnostic observation, result, or abnormality identified during medical evaluation.
- 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_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129bc7ae881909798c64a4c19adad |
completed | April 28, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69e71b384e008190b723c9a0f1089d66 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:32 p.m.