Triple
T19703509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Action API |
E473152
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | MediaWiki core |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: MediaWiki core | Statement: [Action API, partOf, MediaWiki core]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MediaWiki core Context triple: [Action API, partOf, MediaWiki core]
-
A.
MediaWiki
chosen
MediaWiki is a free, open-source wiki software platform designed for collaborative editing of web pages, best known for powering Wikipedia and many other wikis.
-
B.
MediaWiki extensions
MediaWiki extensions are modular add-ons that enhance and customize the functionality of the MediaWiki software beyond its core features.
-
C.
MediaWiki.org
MediaWiki.org is the official website and documentation hub for the MediaWiki software, providing technical resources, manuals, and community collaboration for users and developers.
-
D.
MediaWiki gadgets
MediaWiki gadgets are user-selectable custom tools and interface enhancements, typically written in JavaScript and CSS, that extend and personalize the functionality of MediaWiki-based sites.
-
E.
MediaWiki parser
The MediaWiki parser is the core component of the MediaWiki software that converts wiki markup into HTML, enabling the rendering and display of wiki pages.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b8707081908fbf96c989d2d52d |
completed | April 20, 2026, 3:14 p.m. |
Created at: April 10, 2026, 1:46 p.m.