Triple
T33292259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portola Pharmaceuticals |
E852346
|
entity |
| Predicate | activeIngredientOf |
P184030
|
FINISHED |
| Object | andexanet alfa |
—
|
NE NERFINISHED |
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: andexanet alfa | Statement: [Portola Pharmaceuticals, activeIngredientOf, andexanet alfa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activeIngredientOf Context triple: [Portola Pharmaceuticals, activeIngredientOf, andexanet alfa]
-
A.
isProdrugOf
Indicates that one substance is a precursor form that is metabolized in the body to produce the active form of another substance.
-
B.
drugProduced
Indicates that a particular drug is manufactured or generated by a specified producer or source.
-
C.
hasInactiveIngredient
Indicates that one entity contains another entity as a non-active (inactive) component or ingredient.
-
D.
usesDrug
Indicates that an entity consumes, administers, or otherwise makes use of a specified drug.
-
E.
coatingIngredient
Indicates that one entity serves as an ingredient used to form a coating on another 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_69f349660ff48190a4568803d0b89941 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f7aaabb58c8190bf81673608ecfb6e |
completed | May 3, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f7aa6795f481908940838ee7041ff5 |
completed | May 3, 2026, 8:04 p.m. |
Created at: May 1, 2026, 1:32 a.m.