Triple
T6065093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMN2 |
E135135
|
entity |
| Predicate | geneType |
P68447
|
FINISHED |
| Object | paralog of SMN1 at 5q13 duplication region |
—
|
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: paralog of SMN1 at 5q13 duplication region | Statement: [SMN2, geneType, paralog of SMN1 at 5q13 duplication region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geneType Context triple: [SMN2, geneType, paralog of SMN1 at 5q13 duplication region]
-
A.
genomeCharacteristic
Indicates that an entity has a specific property, feature, or attribute related to its genome.
-
B.
typeOfGSE
Indicates that one entity is classified as a specific type or category of Ground Support Equipment (GSE) in relation to another.
-
C.
targetsGene
Indicates that one entity is directed toward, acts upon, or is intended to affect a specific gene.
-
D.
hasGenomeType
Indicates that an entity possesses or is characterized by a specific type or classification of genome.
-
E.
geneticMaterial
Indicates that one entity serves as the hereditary or genetic substance (e.g., DNA or RNA) of another entity.
- 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_69c00878d06881909ee78e88913bf890 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05723c91c819090b4d4672e72f9f3 |
completed | March 22, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69c049f031408190b08b2766237c5dd0 |
completed | March 22, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69c04e8d4a148190bd8f95caae978e1b |
completed | March 22, 2026, 8:18 p.m. |
Created at: March 22, 2026, 4:10 p.m.