Triple
T6004794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | risdiplam |
E133682
|
entity |
| Predicate | eliminationRoute |
P54020
|
FINISHED |
| Object | mainly via feces |
—
|
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: mainly via feces | Statement: [risdiplam, eliminationRoute, mainly via feces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eliminationRoute Context triple: [risdiplam, eliminationRoute, mainly via feces]
-
A.
hasEliminationRoute
chosen
Indicates that there exists a specific pathway or method by which something can be removed, discharged, or otherwise eliminated from a system or context.
-
B.
loserElimination
Indicates that the entity identified as the loser in a competition, game, or contest is removed or disqualified from further participation.
-
C.
route
Indicates that one entity serves as a path or course used to travel or move between locations associated with another entity.
-
D.
avoidsRoute
Indicates that an entity deliberately does not use or travel along a particular route.
-
E.
reasonForElimination
Indicates the specific cause or justification for why an entity was removed, disqualified, or excluded from consideration.
- 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_69c049e3316c819087ea635fa7ee8472 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:06 p.m.