Triple
T33389025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SARS-CoV-2 spike glycoprotein |
E854994
|
entity |
| Predicate | majorAntigenOf |
P37229
|
FINISHED |
| Object | SARS-CoV-2 |
—
|
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: SARS-CoV-2 | Statement: [SARS-CoV-2 spike glycoprotein, majorAntigenOf, SARS-CoV-2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorAntigenOf Context triple: [SARS-CoV-2 spike glycoprotein, majorAntigenOf, SARS-CoV-2]
-
A.
antigen
chosen
Indicates that one entity functions as an antigen in relation to another, typically provoking or being recognized by an immune response.
-
B.
antigensExpressedOn
Indicates that specific antigens are present on the surface of a given cell or biological structure.
-
C.
antigenLocation
Indicates the location or site within an organism or environment where a specific antigen is present or found.
-
D.
immunityType
Indicates the specific kind or category of immunity that applies in a given context (e.g., legal, diplomatic, medical).
-
E.
isPathogenOf
Indicates that one entity is a disease-causing agent (pathogen) that infects or causes illness in another entity.
- 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_69f3496d54048190a1cb91fdd7caa6ea |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
Created at: May 1, 2026, 1:35 a.m.