Triple
T1103674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tecfidera |
E25438
|
entity |
| Predicate | hasPregnancyCategory |
P23157
|
FINISHED |
| Object | use only if potential benefit justifies potential risk |
—
|
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: use only if potential benefit justifies potential risk | Statement: [Tecfidera, hasPregnancyCategory, use only if potential benefit justifies potential risk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPregnancyCategory Context triple: [Tecfidera, hasPregnancyCategory, use only if potential benefit justifies potential risk]
-
A.
hasCategoryOn
Indicates that something is assigned to or associated with a specific category within a given context or scope.
-
B.
eligibilityCategory
Indicates the classification or type of eligibility that applies to an entity within a given context.
-
C.
hasParentCategory
Indicates that an entity belongs to or is organized under a broader, more general category.
-
D.
hasRelatedCategory
Indicates that one category is associated with another category through a non-hierarchical, contextually relevant relationship.
-
E.
hasCategoryWithin
Indicates that one category is contained within or is a subcategory of another category.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9c375848190baec4d534f489616 |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b7472c848190b0643872f67084a2 |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b7da38888190a118ef20ce4ae9aa |
completed | March 1, 2026, 10:04 p.m. |
Created at: March 1, 2026, 7:43 p.m.