feat(examples): page-by-page entity extraction with multi-model comparison

[ana-daniele]

Summary

Adds examples/example_07_page_entity_extraction.py — a standalone script for extracting MODEL, DATASET, and KPI entities from PDFs page by page, comparing multiple LM Studio-served models.

This complements the existing per-chunk enricher in DoclingEnrichingAgent and is designed for research/evaluation use cases where you want to run several models side-by-side on a document corpus.

Key design choices:

• One API call per page (not per text item) — ~100× fewer calls vs the per-chunk enricher; practical for multi-paper/multi-model batch runs
• Mixed serialisation: text items as plain text, tables as HTML (better structure fidelity for table-heavy papers)
• Mention verification: each extracted mention is checked against the raw page text to flag likely hallucinations
• Consolidated CSV with per-document-per-model aggregate stats (total_entities, hallucination_rate_pct, total_time_s)
• Resumable: skips papers whose output JSON already exists; Docling conversions are cached on disk
• CLI flags: --papers, --out, --url, --test (single-paper smoke test)

Usage

python examples/example_07_page_entity_extraction.py --papers ./papers --out ./runs
# smoke test on first PDF only
python examples/example_07_page_entity_extraction.py --papers ./papers --test

Test plan

• Smoke test with --test flag on a single PDF
• Verify CSV columns and empty-page rows are correct
• Verify HTML output renders correctly
• Confirm model switch via lms CLI works (or graceful skip if CLI not present)

🤖 Generated with Claude Code

[github-actions]

❌ DCO Check Failed

Hi @ana-daniele, your pull request has failed the Developer Certificate of Origin (DCO) check.

This repository supports remediation commits, so you can fix this without rewriting history — but you must follow the required message format.

---

🛠 Quick Fix: Add a remediation commit

Run this command:

git commit --allow-empty -s -m "DCO Remediation Commit for Ana Daniele <ana.daniele@ibm.com>

I, Ana Daniele <ana.daniele@ibm.com>, hereby add my Signed-off-by to this commit: be822be81711b660bc02a704036f532a72854b09
I, Ana Daniele <ana.daniele@ibm.com>, hereby add my Signed-off-by to this commit: 604efda4599e0e713eb4e6dc8151f7593bc70d9c"
git push

---

🔧 Advanced: Sign off each commit directly

For the latest commit:

git commit --amend --signoff
git push --force-with-lease

For multiple commits:

git rebase --signoff origin/main
git push --force-with-lease

More info: DCO check report

[mergify]

Merge Protections

Your pull request matches the following merge protections and will not be merged until they are valid.

🟢 Enforce conventional commit

Wonderful, this rule succeeded.

Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/

• title ~= ^(fix|feat|docs|style|refactor|perf|test|build|ci|chore|revert)(?:\(.+\))?(!)?: