Triple
T2371122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perjeta |
E46091
|
entity |
| Predicate | hasAntibodyType |
P24608
|
FINISHED |
| Object | IgG1 |
—
|
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: IgG1 | Statement: [Perjeta, hasAntibodyType, IgG1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAntibodyType Context triple: [Perjeta, hasAntibodyType, IgG1]
-
A.
antibodyType
chosen
Indicates the specific class or subtype of an antibody involved in the described relationship or context.
-
B.
hasBloodTypeSystem
Indicates that an entity uses or is classified according to a particular blood type classification system (e.g., ABO, Rh).
-
C.
antigen
Indicates that one entity functions as an antigen in relation to another, typically provoking or being recognized by an immune response.
-
D.
hasVaccine
Indicates that one entity possesses, provides, or is associated with a specific vaccine in relation to another entity.
-
E.
hasAntiquark
Indicates that one particle is associated with, or contains, a corresponding antiquark as part of its composition or structure.
- F. None of above.
Provenance (3 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc771302481908540e31abb5aeeba |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.