Triple
T22796833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LOXO-195 |
E564270
|
entity |
| Predicate | hasResistanceContext |
P43585
|
FINISHED |
| Object | acquired resistance to TRK inhibition |
—
|
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: acquired resistance to TRK inhibition | Statement: [LOXO-195, hasResistanceContext, acquired resistance to TRK inhibition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasResistanceContext Context triple: [LOXO-195, hasResistanceContext, acquired resistance to TRK inhibition]
-
A.
isResistant
Indicates that an entity can withstand, oppose, or is not significantly affected by a specified force, influence, or agent.
-
B.
typeOfResistance
chosen
Indicates the kind or category of resistance that characterizes how an entity opposes, impedes, or withstands another entity or influence.
-
C.
methodOfResistance
Indicates a way or technique by which resistance is carried out or expressed.
-
D.
resistedIn
Indicates that an entity actively opposed, withstood, or fought against something within a specific context, event, or location.
-
E.
hasProtectionContext
Indicates that an entity is associated with a specific protection-related context that governs how it is safeguarded or controlled.
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cd9b3c0819096050f43a829ec0d |
completed | April 29, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_69eed2c32e8c8190b73bb9965ed47d64 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:30 p.m.