Triple

T9712358
Position Surface form Disambiguated ID Type / Status
Subject Atril document viewer E235050 entity
Predicate supportsFormat P203 FINISHED
Object DjVu
DjVu is a digital document format designed for efficiently storing and viewing scanned documents, especially those containing a mix of text, line drawings, and photographs, with high compression and fast web viewing.
E816903 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: DjVu | Statement: [Atril document viewer, supportsFormat, DjVu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DjVu
Context triple: [Atril document viewer, supportsFormat, DjVu]
  • A. JPEG 2000
    JPEG 2000 is an image compression standard that improves on the original JPEG by using wavelet-based compression to provide higher quality, better scalability, and advanced features such as lossless compression and region-of-interest coding.
  • B. Pades
    Pades is a village in northwestern Greece located in the mountainous region near Mount Smolikas.
  • C. JPEG
    JPEG is a widely used digital image format that compresses photographic content to reduce file size while maintaining acceptable visual quality.
  • D. ComicView
    ComicView is a stand-up comedy television series that showcased primarily African American comedians and helped launch the careers of many notable performers.
  • E. PostScript
    PostScript is a page description and programming language widely used in desktop publishing and printing to precisely define the layout and appearance of text and graphics.
  • 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: DjVu
Triple: [Atril document viewer, supportsFormat, DjVu]
Generated description
DjVu is a digital document format designed for efficiently storing and viewing scanned documents, especially those containing a mix of text, line drawings, and photographs, with high compression and fast web viewing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: DjVu
Target entity description: DjVu is a digital document format designed for efficiently storing and viewing scanned documents, especially those containing a mix of text, line drawings, and photographs, with high compression and fast web viewing.
  • A. JPEG 2000
    JPEG 2000 is an image compression standard that improves on the original JPEG by using wavelet-based compression to provide higher quality, better scalability, and advanced features such as lossless compression and region-of-interest coding.
  • B. Pades
    Pades is a village in northwestern Greece located in the mountainous region near Mount Smolikas.
  • C. JPEG
    JPEG is a widely used digital image format that compresses photographic content to reduce file size while maintaining acceptable visual quality.
  • D. ComicView
    ComicView is a stand-up comedy television series that showcased primarily African American comedians and helped launch the careers of many notable performers.
  • E. PostScript
    PostScript is a page description and programming language widely used in desktop publishing and printing to precisely define the layout and appearance of text and graphics.
  • 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_69ca84cd8fa0819090a5e243ceb37003 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e0705f8819095852263009c28c5 completed April 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f8c26dc8190a6fa21bde27ba6fa completed April 4, 2026, 11:32 p.m.
NEDg Description generation batch_69d1a0326dd081909e39e422c11cc08f completed April 4, 2026, 11:35 p.m.
NED2 Entity disambiguation (via description) batch_69d1a0c05aa88190a93b0b71bef5c417 completed April 4, 2026, 11:37 p.m.
Created at: March 30, 2026, 8:19 p.m.