Triple
T16851957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Descovy |
E409695
|
entity |
| Predicate | benefitComparedToTDFRegimens |
P118035
|
FINISHED |
| Object | less impact on bone mineral density |
—
|
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: less impact on bone mineral density | Statement: [Descovy, benefitComparedToTDFRegimens, less impact on bone mineral density]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: benefitComparedToTDFRegimens Context triple: [Descovy, benefitComparedToTDFRegimens, less impact on bone mineral density]
-
A.
isIndicatedAsMonotherapyFor
Indicates that a treatment is recommended or used alone, without combination with other therapies, for a particular condition or purpose.
-
B.
regulationComparedTo
Indicates a relationship where one regulation is evaluated, contrasted, or measured in reference to another regulation.
-
C.
isMonotherapy
Indicates that a treatment is used alone, without being combined with any other therapies.
-
D.
hasDifferentBenefitsThan
chosen
Indicates that the benefits provided by one entity are not the same as those provided by another entity.
-
E.
hasBiosimilar
Indicates that one biological product is a biosimilar counterpart to another reference biological product.
- 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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b379b8fc81908d8bc9950c7f8bad |
completed | April 18, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69e32b8cbb048190878a259cc5be960e |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.