Powered by Zoomin Software. For more details please contactZoomin

The Semaphore Fact Extraction Framework (FACTS)

Near Ordered Across Sentence In Paragraph(s)

  • Last Updated: July 8, 2026
  • 2 minute read
    • Semaphore
    • Documentation

Summary

The Near Ordered Across Sentence In Paragraph(s) Context looks for facts and / or anchors each in different sentences in the same paragraph where those are ordered and separated by at most a specified number of words, which is set by the near count metadata.

Usage notes

The count on this extractor refers to the number of tokens (that is, words, and, if you choose to not ignore punctuation, punctuation marks as well) between the sentences that each independently contain an anchor or a fact within a single paragraph.

Fundamental patterns for model and content

If we had an extractor which was an instance of …

with …:

//This

.//

Example model and tests

For an example model of this context extracting facts, please go here:

To test it with the following content go here:

Positive test content

Using this text, we can test the following text which should return the fact:

Some positive content

Some more positive content

Negative test content

All of these texts below should not return anything:

Some negative content

Some more negative content

Near Ordered Across Sentence In Paragraph(s) Context Properties


Mandatory hierarchical relationships

Label Range Constraints
fact Context Elements one or more allowed
or
not anchor Context Elements one or more allowed
or
anchor Context Elements one or more allowed
or
not fact Context Elements one or more allowed

Optional hierarchical relationships

Label Range Constraints
anchor Context Elements one or more allowed
not anchor Context Elements one or more allowed
not fact Context Elements one or more allowed
optional anchor Context Elements one or more allowed
optional fact Context Elements one or more allowed

Mandatory associative relationships

Label Range Constraints
(none)

Optional associative relationships

Label Range Constraints
depended on by context Contexts only one allowed
depends on context Contexts only one allowed
extract fact as Fact Name only one allowed
group fact as Fact Name only one allowed
location Locations only one allowed
precluded by context Contexts only one allowed
precludes context Contexts only one allowed
punctuation Punctuation rules only one allowed

Mandatory alternative labels

Label Range Constraints
(none)

Optional alternative labels

Label Range Constraints
(none)

Mandatory metadata

Label Range Constraints
near count Integer only one allowed

Optional metadata

Label Range Constraints
context position from document end Integer only one allowed
context position from document start Integer only one allowed
fact position from context end Integer only one allowed
fact position from context start Integer only one allowed
field String only one allowed
width for context Integer only one allowed
return group fact ID Boolean only one allowed
return raw text also Boolean only one allowed
return value using regex String only one allowed
{1-10} greedy repeat Integer one or more allowed
{1-10} non-greedy repeat Integer one or more allowed
debug Boolean only one allowed
TitleResults for “How to create a CRG?”Also Available inAlert