Triple
T6005171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tegsedi |
E133690
|
entity |
| Predicate | reducesRiskOf |
P9925
|
FINISHED |
| Object | progression of polyneuropathy in hATTR patients |
—
|
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: progression of polyneuropathy in hATTR patients | Statement: [Tegsedi, reducesRiskOf, progression of polyneuropathy in hATTR patients]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reducesRiskOf Context triple: [Tegsedi, reducesRiskOf, progression of polyneuropathy in hATTR patients]
-
A.
reduces
chosen
Indicates that one entity causes a decrease in the amount, intensity, degree, or impact of another entity.
-
B.
riskElement
Indicates that one entity is a risk-related component, factor, or contributor associated with another entity within a risk context.
-
C.
riskTaken
Indicates that an entity has undertaken an action or decision involving exposure to potential loss, harm, or uncertainty.
-
D.
riskBasis
Indicates the underlying factor, condition, or rationale that forms the basis for assessing or assigning risk in a given context.
-
E.
safetyRationale
Indicates the reasoning or justification provided to explain how and why something is considered safe or made safe.
- 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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f10d18081908c351170b7f58d3d |
completed | March 22, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69c049e4daf4819099bf870dc700e0a2 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:06 p.m.