Triple
T22796926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMN complex |
E564273
|
entity |
| Predicate | hasComponent |
P35
|
FINISHED |
| Object | UNRIP protein |
—
|
NE NERFINISHED |
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: UNRIP protein | Statement: [SMN complex, hasComponent, UNRIP protein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UNRIP protein Context triple: [SMN complex, hasComponent, UNRIP protein]
-
A.
M2 protein
M2 protein is a regulatory protein of respiratory syncytial virus that plays key roles in viral transcription and replication.
-
B.
U1 snRNP
U1 snRNP is a small nuclear ribonucleoprotein complex essential for recognizing the 5′ splice site and initiating pre-mRNA splicing in eukaryotic cells.
-
C.
Sm proteins
chosen
Sm proteins are a family of small, evolutionarily conserved RNA-binding proteins that form the core of small nuclear ribonucleoproteins (snRNPs) essential for pre-mRNA splicing in eukaryotic cells.
-
D.
Serpins
Serpins is a civil parish in the municipality of Lousã in central Portugal, known for its natural landscapes and proximity to the Serra da Lousã.
-
E.
F protein
F protein is a viral fusion glycoprotein of respiratory syncytial virus that enables the virus to fuse with and enter host cells.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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. |
Created at: April 17, 2026, 3:30 p.m.