Triple
T31535828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Symmetrel |
E804596
|
entity |
| Predicate | wasFirstApprovedFor |
P171942
|
FINISHED |
| Object | prophylaxis and treatment of influenza A |
—
|
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: prophylaxis and treatment of influenza A | Statement: [Symmetrel, wasFirstApprovedFor, prophylaxis and treatment of influenza A]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasFirstApprovedFor Context triple: [Symmetrel, wasFirstApprovedFor, prophylaxis and treatment of influenza A]
-
A.
wasFirstApprovedIn
Indicates the time or context in which something (such as a proposal, product, or document) received its initial official approval.
-
B.
isApprovedFor
Indicates that one entity has been officially authorized, accepted, or permitted for use, access, or association with another entity.
-
C.
wasFirst
Indicates that one entity occurred, appeared, or held a position before another in time or sequence.
-
D.
approvedAt
Indicates the date and time at which an entity received formal approval.
-
E.
wasFirstOf
Indicates that the subject is the earliest or initial instance in a series, sequence, or group of similar entities or events.
- 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_69f348d03ef88190a2b73d7b94b9e02d |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a956e9b08190bf83547bba8e8147 |
completed | May 3, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69f6a75656e081908739ed9e2f600e42 |
completed | May 3, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f6a8036ab481908019f2f071fa406e |
completed | May 3, 2026, 1:42 a.m. |
Created at: April 30, 2026, 10:03 p.m.