Triple
T1684958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMT Division |
E36421
|
entity |
| Predicate | treatsCondition |
P8786
|
FINISHED |
| Object | hematologic malignancies |
—
|
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: hematologic malignancies | Statement: [BMT Division, treatsCondition, hematologic malignancies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatsCondition Context triple: [BMT Division, treatsCondition, hematologic malignancies]
-
A.
treats
chosen
Indicates that one entity provides medical care or therapeutic intervention to another entity.
-
B.
conditions
Indicates that one entity specifies or imposes requirements, constraints, or circumstances that must be satisfied or hold true for another entity or situation.
-
C.
treatment
Indicates that one entity is used as a medical or therapeutic intervention to address, manage, or cure a condition affecting another entity.
-
D.
typeOfRemedy
Indicates that one entity is a specific kind or category of remedy in relation to another entity.
-
E.
coreCondition
Indicates that something serves as the primary or fundamental condition that must hold for a situation, process, or relationship to apply.
- 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_69a886151508819084fa7f1ce6e05577 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aba644070c81908745b56d981fe273 |
completed | March 7, 2026, 4:15 a.m. |
| PD | Predicate disambiguation | batch_69aa61b57a6881909373af287ef24799 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:29 p.m.