Triple
T28938901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HTT |
E730391
|
entity |
| Predicate | hasMutationType |
P68674
|
FINISHED |
| Object | CAG trinucleotide 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: CAG trinucleotide repeat expansion | Statement: [HTT, hasMutationType, CAG trinucleotide repeat expansion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMutationType Context triple: [HTT, hasMutationType, CAG trinucleotide repeat expansion]
-
A.
hasMutationSystem
Indicates that one entity possesses or employs a particular mutation system or mechanism for generating or managing mutations.
-
B.
hasTransitionType
Indicates the type or category of transition that occurs between two states, phases, or conditions.
-
C.
mutationType
chosen
Indicates the specific kind or category of genetic alteration that has occurred in an entity.
-
D.
hasOperationType
Indicates the specific kind or category of operation associated with an entity or process.
-
E.
hasMoveType
Indicates that an action or move is associated with a specific type or category (such as elemental, functional, or classification-based).
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 28, 2026, 8:34 a.m.