Triple
T23186796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | REGN-COV2 |
E579612
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | REGN-COV |
—
|
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: REGN-COV | Statement: [REGN-COV2, alsoKnownAs, REGN-COV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: REGN-COV Context triple: [REGN-COV2, alsoKnownAs, REGN-COV]
-
A.
REGN-COV2
chosen
REGN-COV2 is a monoclonal antibody cocktail designed to prevent and treat COVID-19 by targeting the SARS-CoV-2 virus.
-
B.
Vaxzevria COVID-19 vaccine
Vaxzevria COVID-19 vaccine is a viral vector coronavirus vaccine created to prevent COVID-19 infection and severe disease in adults.
-
C.
Comirnaty
Comirnaty is the brand name of the Pfizer–BioNTech mRNA COVID-19 vaccine used worldwide for the prevention of coronavirus infection.
-
D.
mRNA-1273
mRNA-1273 is a messenger RNA–based COVID-19 vaccine that instructs cells to produce the SARS-CoV-2 spike protein to elicit an immune response.
-
E.
molnupiravir
Molnupiravir is an oral antiviral medication used to treat COVID-19 by inhibiting replication of the SARS-CoV-2 virus.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fd3aaa08190b9cf7afe4ee5a38d |
completed | April 29, 2026, 4:57 a.m. |
Created at: April 17, 2026, 4:05 p.m.