interactions disappeared between 20201001 and 20201101 nt files

[realmarcin]

Describe the bug

A triple for interacts_with between ACE2 and GLP1R is present in the 20201001 release but not 20201101.

To Reproduce

This triple:
P43220 interacts_with Q9BYF1

Is present in the .nt file from 20201001:
https://kg-hub.berkeleybop.io/kg-covid-19/20201001/kg-covid-19.nt.gz

but not in the 20201101 one:
https://kg-hub.berkeleybop.io/kg-covid-19/20201101/kg-covid-19.nt.gz

Note that this triple is also not present in the 20201001 .tsv (see here #375).

Here are all the relevant triples from the 202021101 .nt file:
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f http://www.w3.org/1999/02/22-rdf-syntax-ns#subject http://identifiers.org/uniprot/Q9BYF1 .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f http://www.w3.org/1999/02/22-rdf-syntax-ns#predicate https://w3id.org/biolink/vocab/interacts_with .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f http://www.w3.org/1999/02/22-rdf-syntax-ns#object http://identifiers.org/uniprot/P43220 .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://w3id.org/biolink/vocab/relation http://purl.obolibrary.org/obo/RO_0002434 .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://w3id.org/biolink/vocab/provided_by "STRING" .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f http://www.w3.org/1999/02/22-rdf-syntax-ns#type "biolink:Association"^^http://www.w3.org/2001/XMLSchema#string .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/combined_score "157.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/neighborhood "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/neighborhood_transferred "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/fusion "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/cooccurence "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/homology "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/coexpression "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/coexpression_transferred "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/experiments "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/experiments_transferred "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/database "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/database_transferred "0.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/textmining "108.0"^^http://www.w3.org/2001/XMLSchema#float .
urn:uuid:1aad7d40-aa7a-4ec1-87c9-85108b3eb77f https://www.example.org/UNKNOWN/textmining_transferred "94.0"^^http://www.w3.org/2001/XMLSchema#float .

Expected behavior

Unclear why this interaction disappeared later.

Version

20201001 vs 20201101

Additional context

related to #375

[kliegr]

Is it possible to track the provenance of this triple when it was still present in the .nt file?

The "metadata"/reification triples retrieved for P43220 interacts_with Q9BYF1 are listed in the issue, but none of those seems to actually point to a publication from which this triple was presumably extracted.

Could the disappearance of the triple be related to possible low extraction confidence? In this respect, is information such as
ex:textmining = "108.0" or textmining_transferred= "94.0" of any significance?

Is the semantics of predicates (textmining_transferred, textmining, combined_score) documented somewhere?