apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-07-10 05:42:12 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix/extraction prov (#662)

Browse source 
Quoted triple fixes, including...

1. Updated triple_provenance_triples() in triples.py:
   - Now accepts a Triple object directly
   - Creates the reification triple using TRIPLE term type: stmt_uri tg:reifies
         <<extracted_triple>>
   - Includes it in the returned provenance triples
    
2. Updated definitions extractor:
   - Added imports for provenance functions and component version
   - Added ParameterSpec for optional llm-model and ontology flow parameters
   - For each definition triple, generates provenance with reification
    
3. Updated relationships extractor:
   - Same changes as definitions extractor
This commit is contained in:
cybermaggedon 2026-03-06 12:23:58 +00:00 • committed by GitHub
parent cd5580be59
commit 2b9232917c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 361 additions and 72 deletions
Download patch file Download diff file Expand all files Collapse all files

32
trustgraph-flow/trustgraph/extract/kg/definitions/extract.py
View file

@ -18,7 +18,10 @@ from .... schema import PromptRequest, PromptResponse
from .... rdf import TRUSTGRAPH_ENTITIES, DEFINITION, RDF_LABEL, SUBJECT_OF
from .... base import FlowProcessor, ConsumerSpec, ProducerSpec
from .... base import PromptClientSpec
from .... base import PromptClientSpec, ParameterSpec
from .... provenance import statement_uri, triple_provenance_triples
from .... flow_version import __version__ as COMPONENT_VERSION
DEFINITION_VALUE = Term(type=IRI, iri=DEFINITION)
RDF_LABEL_VALUE = Term(type=IRI, iri=RDF_LABEL)
@ -75,6 +78,10 @@ class Processor(FlowProcessor):
)
)
# Optional flow parameters for provenance
self.register_specification(ParameterSpec("llm-model"))
self.register_specification(ParameterSpec("ontology"))
def to_uri(self, text):
part = text.replace(" ", "-").lower().encode("utf-8")
@ -132,6 +139,10 @@ class Processor(FlowProcessor):
chunk_doc_id = v.document_id if v.document_id else v.metadata.id
chunk_uri = v.metadata.id # The URI form for the chunk
# Get optional provenance parameters
llm_model = flow("llm-model")
ontology_uri = flow("ontology")
# Note: Document metadata is now emitted once by librarian at processing
# initiation, so we don't need to duplicate it here.
@ -157,9 +168,24 @@ class Processor(FlowProcessor):
o=Term(type=LITERAL, value=s),
))
triples.append(Triple(
# The definition triple - this is the main extracted fact
definition_triple = Triple(
s=s_value, p=DEFINITION_VALUE, o=o_value
))
)
triples.append(definition_triple)
# Generate provenance for the definition triple (reification)
stmt_uri = statement_uri()
prov_triples = triple_provenance_triples(
stmt_uri=stmt_uri,
extracted_triple=definition_triple,
chunk_uri=chunk_uri,
component_name=default_ident,
component_version=COMPONENT_VERSION,
llm_model=llm_model,
ontology_uri=ontology_uri,
)
triples.extend(prov_triples)
# Link entity to chunk (not top-level document)
triples.append(Triple(

32
trustgraph-flow/trustgraph/extract/kg/relationships/extract.py
View file

@ -18,7 +18,10 @@ from .... schema import PromptRequest, PromptResponse
from .... rdf import RDF_LABEL, TRUSTGRAPH_ENTITIES, SUBJECT_OF
from .... base import FlowProcessor, ConsumerSpec, ProducerSpec
from .... base import PromptClientSpec
from .... base import PromptClientSpec, ParameterSpec
from .... provenance import statement_uri, triple_provenance_triples
from .... flow_version import __version__ as COMPONENT_VERSION
RDF_LABEL_VALUE = Term(type=IRI, iri=RDF_LABEL)
SUBJECT_OF_VALUE = Term(type=IRI, iri=SUBJECT_OF)
@ -65,6 +68,10 @@ class Processor(FlowProcessor):
)
)
# Optional flow parameters for provenance
self.register_specification(ParameterSpec("llm-model"))
self.register_specification(ParameterSpec("ontology"))
def to_uri(self, text):
part = text.replace(" ", "-").lower().encode("utf-8")
@ -113,6 +120,10 @@ class Processor(FlowProcessor):
chunk_doc_id = v.document_id if v.document_id else v.metadata.id
chunk_uri = v.metadata.id # The URI form for the chunk
# Get optional provenance parameters
llm_model = flow("llm-model")
ontology_uri = flow("ontology")
# Note: Document metadata is now emitted once by librarian at processing
# initiation, so we don't need to duplicate it here.
@ -142,11 +153,26 @@ class Processor(FlowProcessor):
else:
o_value = Term(type=LITERAL, value=str(o))
triples.append(Triple(
# The relationship triple - this is the main extracted fact
relationship_triple = Triple(
s=s_value,
p=p_value,
o=o_value
))
)
triples.append(relationship_triple)
# Generate provenance for the relationship triple (reification)
stmt_uri = statement_uri()
prov_triples = triple_provenance_triples(
stmt_uri=stmt_uri,
extracted_triple=relationship_triple,
chunk_uri=chunk_uri,
component_name=default_ident,
component_version=COMPONENT_VERSION,
llm_model=llm_model,
ontology_uri=ontology_uri,
)
triples.extend(prov_triples)
# Label for s
triples.append(Triple(