Triple
T19703444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MediaWiki extensions |
E473151
|
entity |
| Predicate | example |
P1259
|
FINISHED |
| Object |
Cite extension
The Cite extension is a MediaWiki add-on that enables easy insertion and management of footnotes and references within wiki pages.
|
E1391274
|
NE FINISHED |
How this triple was built (4 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: Cite extension | Statement: [MediaWiki extensions, example, Cite extension]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cite extension Context triple: [MediaWiki extensions, example, Cite extension]
-
A.
BCite
BCite is a legal citation and research service that competes with KeyCite by providing tools to track the history, treatment, and validity of legal authorities.
-
B.
InCites
InCites is a research analytics platform that provides citation-based metrics and benchmarking tools to evaluate institutional and researcher performance.
-
C.
Citation
Citation is a compact car model name used by Chevrolet, most notably for its front-wheel-drive Chevrolet Citation produced in the late 1970s and 1980s.
-
D.
RefWorks
RefWorks is a web-based reference management tool that helps researchers collect, organize, and format citations and bibliographies in various academic styles.
-
E.
BibTeX
BibTeX is a tool and file format used with LaTeX to manage and format bibliographic references in scholarly documents.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cite extension Triple: [MediaWiki extensions, example, Cite extension]
Generated description
The Cite extension is a MediaWiki add-on that enables easy insertion and management of footnotes and references within wiki pages.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cite extension Target entity description: The Cite extension is a MediaWiki add-on that enables easy insertion and management of footnotes and references within wiki pages.
-
A.
BCite
BCite is a legal citation and research service that competes with KeyCite by providing tools to track the history, treatment, and validity of legal authorities.
-
B.
InCites
InCites is a research analytics platform that provides citation-based metrics and benchmarking tools to evaluate institutional and researcher performance.
-
C.
Citation
Citation is a compact car model name used by Chevrolet, most notably for its front-wheel-drive Chevrolet Citation produced in the late 1970s and 1980s.
-
D.
RefWorks
RefWorks is a web-based reference management tool that helps researchers collect, organize, and format citations and bibliographies in various academic styles.
-
E.
BibTeX
BibTeX is a tool and file format used with LaTeX to manage and format bibliographic references in scholarly documents.
- F. None of above. chosen
Provenance (5 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. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ab98bda48190b61ac274459954bd |
completed | May 15, 2026, 11:26 p.m. |
| NEDg | Description generation | batch_6a07acc9e5488190ba55f47af118fca2 |
completed | May 15, 2026, 11:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07ad8aefc4819098768025121123ba |
completed | May 15, 2026, 11:34 p.m. |
Created at: April 10, 2026, 1:46 p.m.