Developer fixes entity resolution pipeline after news text exposed critical flaws

·27 views

A developer building the entity resolution pipeline at 2asy.ai discovered major gaps after expanding from structured registry data to news articles, triggering two weeks of cleanup. The core problem was that news sources use informal company names — such as '삼성' instead of '삼성전자 주식회사' — which caused the pipeline's character-based blocking rule to match a short mention against every Samsung subsidiary at once. To address this, the developer added a post-scoring filter that uses surrounding article context, such as nearby entity mentions and sector keywords, to disambiguate top-scoring candidates. A stricter confidence threshold was also introduced specifically for short or informal name mentions, requiring a 0.90 score before merging them to a registry entry. However, the developer acknowledges the underlying benchmark still uses only registry-vs-registry pairs, leaving precision and recall for news-domain mentions unmeasured.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

osFoundry adds a prompt library with versioning and reusable skills for agents

osFoundry, a desktop app combining chat, agents, files and tools, now includes a Prompt Library that gathers prompts in one searchable place with favorites and usage counts. Users can save edits either by overwriting a prompt or as a new version, keeping earlier wording available for reuse. Prompts can contain placeholders such as {{product}} that the app fills in through a simple form before inserting the text into the chat. Proven prompts can also be converted into skills in Studio, which agents use automatically when a task matches their trigger and assigned tools.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Testing a pump underload detector before it controls a motor

A running pump may draw less current when it loses load, but a low current reading alone cannot confirm a dry pump, so the detector should report suspected underload with supporting context. Measurements should begin only after the motor is confirmed running and the startup window has passed, and mismatches between run commands and contactor feedback should be logged. Missing, stale, or invalid current data should be treated as a sensor fault rather than as zero current. The alert should use its own persistence timer and reset when readings return to normal, while latched alarms, motor-stop logic, and protection hardware remain independent of the telemetry. Validation should involve replaying simulated traces, comparing results against normal operation at several operating points, and logging timestamps, RMS current, motor state, thresholds, and fault reasons.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Solana token rules can be verified with a single RPC call, no SDK needed

A developer published a method for reading a Solana token's rules using one standard RPC request, requiring no SDK, wallet, or keys. The approach decodes the token's mint account to reveal its owner program, mint and freeze authorities, and Token-2022 extensions such as transfer fees, transfer hooks, and permanent delegates. The author applies the check weekly to one token and says it recently corrected earlier documentation that had misstated the token's technical setup. Using the method on the WEN mint, the author found it runs on the original SPL Token program with authorities revoked and no extensions. The post argues that repeatable, rerunnable checks provide stronger evidence than one-time snapshots.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Adding Captions and Chapters to a Product Demo Video in an Afternoon

A product demo landing page autoplayed muted, and a hard-of-hearing teammate and analytics showed that most visitors never unmuted it. The author added accurate captions and chapter markers using only a text editor and HTML, without a video platform or paid captioning service. Captions were generated by uploading the MP4 to an audio-to-text tool and exporting WebVTT, with language set explicitly and speaker recognition disabled. A small Node script was used to flag cues exceeding two lines or 42 characters per line, and chapters were created as a separate VTT file with timestamps found by searching the transcript. The captions track is set to load by default in the HTML track element, and a clickable chapter list was built with JavaScript.

0 comments Read more at DEV Community