Triple
T6004777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | risdiplam |
E133682
|
entity |
| Predicate | administrationWithFood |
P68666
|
FINISHED |
| Object | can be taken with or without food |
—
|
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: can be taken with or without food | Statement: [risdiplam, administrationWithFood, can be taken with or without food]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: administrationWithFood Context triple: [risdiplam, administrationWithFood, can be taken with or without food]
-
A.
administersFoodPackages
Indicates that one entity provides or distributes food packages to another entity.
-
B.
usesFood
Indicates that one entity employs or consumes a food item as a resource, ingredient, or means to achieve some purpose.
-
C.
eatingPermitted
Indicates that an entity is allowed or authorized to eat in a given context or situation.
-
D.
mayBeGivenTo
Indicates that something is permitted or eligible to be transferred, assigned, or provided from one entity to another.
-
E.
nutritionTitleAdministeredBy
Indicates that a specific nutrition-related title, role, or designation is assigned or granted by a particular administering authority or 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_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. |
| PDg | Predicate description generation | batch_69c04e8c5bfc8190b986a7071d1b23e3 |
completed | March 22, 2026, 8:18 p.m. |
Created at: March 22, 2026, 4:06 p.m.