Triple
T19703571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Semantic MediaWiki |
E473153
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Wikidata |
—
|
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: Wikidata | Statement: [Semantic MediaWiki, relatedTo, Wikidata]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wikidata Context triple: [Semantic MediaWiki, relatedTo, Wikidata]
-
A.
Wikidata
chosen
Wikidata is a collaboratively edited, multilingual knowledge base that provides structured data to support Wikipedia and other Wikimedia projects.
-
B.
Wikidata Query Service
Wikidata Query Service is an online SPARQL endpoint and interface that allows users to query and explore structured data stored in Wikidata.
-
C.
Wikibase
Wikibase is a free, open-source software suite developed by Wikimedia for storing, managing, and querying structured, linked data.
-
D.
Wikidata development team
The Wikidata development team is the group of software engineers and product specialists responsible for building and maintaining the Wikidata project under Wikimedia Deutschland.
-
E.
Korean Wikidata
Korean Wikidata is the Korean-language edition of Wikidata, a collaboratively edited knowledge base that stores structured data to support Wikimedia projects and beyond.
- 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.