Triple
T2190757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Janssen COVID-19 Vaccine |
E49854
|
entity |
| Predicate | antigen |
P37229
|
FINISHED |
| Object | SARS-CoV-2 spike protein |
—
|
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: SARS-CoV-2 spike protein | Statement: [Janssen COVID-19 Vaccine, antigen, SARS-CoV-2 spike protein]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: antigen Context triple: [Janssen COVID-19 Vaccine, antigen, SARS-CoV-2 spike protein]
-
A.
antibodyType
Indicates the specific class or subtype of an antibody involved in the described relationship or context.
-
B.
annex
Indicates the act of formally incorporating one entity, typically a territory, into the domain or control of another.
-
C.
pathogenType
Indicates the specific kind or category of pathogen associated with or responsible for an entity or condition.
-
D.
seal
Indicates that an agent closes or fastens something so that it is securely shut and often airtight or watertight.
-
E.
antagonistOf
Indicates a relationship where one entity actively opposes, conflicts with, or serves as an adversary to another.
- 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_69a88aaba3c48190b351cab9b26989ff |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbf9e99f08190892d34485c8f2f25 |
completed | March 7, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_69abbda32d1881909d1fd83a751fb21c |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbf9c77fc8190a323bcaf644fb2c5 |
completed | March 7, 2026, 6:03 a.m. |
Created at: March 4, 2026, 7:46 p.m.