Triple
T25614439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abbreviated New Drug Application process |
E642120
|
entity |
| Predicate | referenceProduct |
P162893
|
FINISHED |
| Object | reference listed drug |
—
|
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: reference listed drug | Statement: [Abbreviated New Drug Application process, referenceProduct, reference listed drug]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referenceProduct Context triple: [Abbreviated New Drug Application process, referenceProduct, reference listed drug]
-
A.
providedProduct
Indicates that one entity has supplied or made available a particular product to another entity.
-
B.
byProduct
Indicates that one entity is produced incidentally or as a secondary result of a process, activity, or creation involving another entity.
-
C.
vendorProductOf
Indicates that a product is offered or supplied by a particular vendor.
-
D.
referencesBrand
Indicates that one entity mentions, cites, or otherwise refers to a specific brand in its content or context.
-
E.
referenceSectionFor
Indicates a relationship where one resource serves as the reference section or reference material specifically associated with another resource.
- 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_69e77e7a96748190b10f2699041e4e43 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f62e83045c8190a424a2e401a88e9e |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_69f62d886828819080ec2f742b9449e3 |
completed | May 2, 2026, 4:59 p.m. |
Created at: April 21, 2026, 4:58 p.m.