Triple
T22796824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LOXO-195 |
E564270
|
entity |
| Predicate | bindingTarget |
P149746
|
FINISHED |
| Object | mutant TRK proteins |
—
|
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: mutant TRK proteins | Statement: [LOXO-195, bindingTarget, mutant TRK proteins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bindingTarget Context triple: [LOXO-195, bindingTarget, mutant TRK proteins]
-
A.
bindingFor
Indicates that one entity serves as the binding, constraint, or linkage mechanism that determines how another entity is associated, applied, or made effective.
-
B.
bindingAsTo
Indicates that one entity is legally or contractually binding upon another entity with respect to certain terms, obligations, or conditions.
-
C.
bindingOption
Indicates a relationship where one entity specifies or constrains how another entity is bound, attached, or associated within a given context or configuration.
-
D.
mappingTarget
Indicates that one entity serves as the destination or result of a mapping defined from another entity.
-
E.
bindingOn
Indicates that one party is legally or formally obligated to follow, accept, or be governed by a decision, rule, or agreement established by another.
- 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_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. |
| PDg | Predicate description generation | batch_69eeeb5681f88190821129ced752f190 |
completed | April 27, 2026, 4:51 a.m. |
Created at: April 17, 2026, 3:30 p.m.