Triple
T22796957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMN complex |
E564273
|
entity |
| Predicate | defectLeadsTo |
P18658
|
FINISHED |
| Object | reduced snRNP levels |
—
|
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: reduced snRNP levels | Statement: [SMN complex, defectLeadsTo, reduced snRNP levels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defectLeadsTo Context triple: [SMN complex, defectLeadsTo, reduced snRNP levels]
-
A.
defect
Indicates that an entity has a fault, imperfection, or malfunction that causes it to deviate from an expected standard or proper functioning.
-
B.
defectsFrom
Indicates a relationship where an entity abandons, deserts, or switches allegiance away from another entity, often to join an opposing side.
-
C.
reasonForDefect
Indicates the cause or underlying reason that led to the occurrence of a particular defect.
-
D.
canLeadTo
chosen
Indicates that one entity, condition, or event has the potential to cause, result in, or bring about another.
-
E.
damageLeadsTo
Indicates that one instance of damage causally results in or contributes to another specified outcome or condition.
- 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.