Triple
T4392583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | non-Hodgkin lymphoma |
E99398
|
entity |
| Predicate | hasPrognosticFactor |
P56354
|
FINISHED |
| Object | age |
—
|
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: age | Statement: [non-Hodgkin lymphoma, hasPrognosticFactor, age]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrognosticFactor Context triple: [non-Hodgkin lymphoma, hasPrognosticFactor, age]
-
A.
hasPrognosis
Indicates that one entity (typically a medical condition or case) is associated with an expected course or outcome over time, such as likely progression, duration, or chances of recovery.
-
B.
hasPreclinicalFeature
Indicates that an entity exhibits a characteristic, sign, or attribute that is present before the full clinical manifestation of a condition or disease.
-
C.
hasClinicalSignificance
Indicates that something (such as a finding, variant, or condition) has a meaningful impact or relevance in a clinical or medical context.
-
D.
riskFactorTypeStudied
Indicates that a particular type of risk factor is the subject of study or analysis in a given context.
-
E.
diagnosticBiomarker
Indicates that one entity serves as a measurable biological indicator used to detect, confirm, or help diagnose a condition or disease in another entity.
- F. None of above. chosen
Provenance (4 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_69b345506b408190b0e3dee616738a7d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35285592881909fcdea225a655950 |
completed | March 12, 2026, 11:55 p.m. |
| PD | Predicate disambiguation | batch_69b34f572efc8190bad1e5078cbcb75a |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b3501834448190bedf775a80da4778 |
completed | March 12, 2026, 11:45 p.m. |
Created at: March 12, 2026, 11:19 p.m.