Triple
T34091551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | vigabatrin |
E874312
|
entity |
| Predicate | shouldBeUsedWhen |
P178221
|
FINISHED |
| Object | benefits outweigh risk of vision loss |
—
|
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: benefits outweigh risk of vision loss | Statement: [vigabatrin, shouldBeUsedWhen, benefits outweigh risk of vision loss]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shouldBeUsedWhen Context triple: [vigabatrin, shouldBeUsedWhen, benefits outweigh risk of vision loss]
-
A.
shouldNotBeUsedWith
Indicates that one entity is not recommended or is prohibited from being used in combination with another entity.
-
B.
mustBeUsed
Indicates that one entity is required or obligated to be utilized or applied in relation to another entity or context.
-
C.
shouldNotBeUsedIn
Indicates that one entity is not appropriate, allowed, or recommended for use within the context, scope, or situation defined by another entity.
-
D.
exportUse
Indicates that something is used, intended, or suitable for export from one place or market to another.
-
E.
usedFor
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
- 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_69f349a735208190a1dbfb1c2a121059 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f70c53062c8190b4cb7be22ab00bc7 |
completed | May 3, 2026, 8:50 a.m. |
| PD | Predicate disambiguation | batch_69f70ac0170c819098e3b8e41d02efef |
completed | May 3, 2026, 8:43 a.m. |
| PDg | Predicate description generation | batch_69f70b94784c8190970d654e066eb50d |
completed | May 3, 2026, 8:47 a.m. |
Created at: May 1, 2026, 1:52 a.m.