Powered by Zoomin Software. For more details please contactZoomin

The Semaphore Fact Extraction Framework (FACTS)

Sequenced Across Paragraphs In Document

  • Last Updated: May 29, 2026
  • 2 minute read
    • Semaphore
    • Documentation

Summary

The Sequenced Across Paragraphs In Document Context looks for sequenced paragraphs (i.e. they are in a specific order). These can be separated by any number of paragraphs to skip. However, the extractor does not require skips, nor does it require anchors: it does require at least one fact.

Usage Notes

Use this context when the anchors and facts you are interested in are contained in sequential paragraphs within a document. If you use the “loose” metadata attribute, the sequence will also look within the same paragraph for a fact and anchor. Note that the elements of this context must be listed in the correct sequence using the ORDERED LIST in the Narrower Concepts section.

Sequenced Across Paragraphs In Document Contexts Properties

The following table is common to all of the Sequenced Across Paragraphs In Document Contexts.

Hierarchical relationships

Label Range Require/Optional Constraints
anchor Context Elements
At least

one of these

is Required
one or more allowed
captured fact Captured Fact :::
fact 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 Optional one or more allowed
optional fact Context Elements Optional one or more allowed
skip Skip Optional one or more allowed

Associative relationships

Label Range Require/Optional Constraints
depended on by context Contexts Optional only one allowed
depends on context Contexts Optional only one allowed
extract fact as Fact Name Optional only one allowed
group fact as Fact Name Optional only one allowed
location Locations Optional only one allowed
precluded by context Contexts Optional only one allowed
precludes_context Contexts Optional only one allowed
Punctuation Punctuation rules Optional only one allowed

Alternative labels

None


Metadata

Label Range Require/Optional Constraints
context position from document end Integer Optional only one allowed
context position from document start Integer Optional only one allowed
fact position from context end Integer Optional only one allowed
fact position from context start Integer Optional only one allowed
field String Optional only one allowed
loose Boolean Optional only one allowed
return group fact ID Boolean Optional only one allowed
return raw text also Boolean Optional only one allowed
return value using regex String Optional only one allowed
{1-10} greedy repeat Integer Optional one or more allowed
{1-10} non-greedy repeat Integer Optional one or more allowed

Example model and tests

TitleResults for “How to create a CRG?”Also Available inAlert