Triple
T10825790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | reStructuredText |
E255494
|
entity |
| Predicate | parsedBy |
P33283
|
FINISHED |
| Object | Pandoc |
E695751
|
NE FINISHED |
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: Pandoc | Statement: [reStructuredText, parsedBy, Pandoc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pandoc Context triple: [reStructuredText, parsedBy, Pandoc]
-
A.
Pandoc
chosen
Pandoc is a powerful open-source document converter that can transform files between numerous markup and word-processing formats, widely used for working with Markdown and other text formats.
-
B.
MultiMarkdown
MultiMarkdown is an extended version of the Markdown markup language that adds features like tables, footnotes, citations, and document metadata for more complex publishing needs.
-
C.
LaTeX
LaTeX is a widely used, high-quality typesetting system particularly popular in academia for producing technical and scientific documents with precise control over layout and mathematical notation.
-
D.
CommonMark
CommonMark is a standardized, highly compatible specification of Markdown syntax designed to eliminate ambiguities and ensure consistent rendering across different implementations.
-
E.
R Markdown
R Markdown is a file format and authoring framework that combines R code with narrative text to create dynamic, reproducible documents, reports, and presentations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d734d0389c819090a892693c4046ed |
completed | April 9, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de858672d8819094baf4fe98b8dea4 |
completed | April 14, 2026, 6:20 p.m. |
Created at: April 8, 2026, 9:19 p.m.