Triple
T22693353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | C9orf72 |
E561105
|
entity |
| Predicate | pathogenicVariantType |
P97055
|
FINISHED |
| Object | large hexanucleotide repeat expansion |
—
|
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: large hexanucleotide repeat expansion | Statement: [C9orf72, pathogenicVariantType, large hexanucleotide repeat expansion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pathogenicVariantType Context triple: [C9orf72, pathogenicVariantType, large hexanucleotide repeat expansion]
-
A.
genomicAlteration
chosen
Indicates a relationship where an entity has undergone a change or mutation in its genetic material compared to a reference genome.
-
B.
geneType
Indicates the specific category or classification of a gene based on its functional or structural characteristics.
-
C.
pathogenType
Indicates the specific kind or category of pathogen associated with or responsible for an entity or condition.
-
D.
protectiveAlleleForDisease
Indicates that the presence of a specific allele reduces the risk, severity, or likelihood of developing a particular disease.
-
E.
riskAlleleForDisease
Indicates that a specific allele is associated with an increased risk of developing a particular disease.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789c6ae481908975b7d27e7624ac |
completed | April 29, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69ee62b2259c819091ed1387a748b9f3 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:13 p.m.