Triple

T3571153
Position Surface form Disambiguated ID Type / Status
Subject Project Gutenberg E75572 entity
Predicate fileFormat P130 FINISHED
Object EPUB
EPUB is a widely used open e-book file format designed for reflowable digital publications that can adapt to different screen sizes and devices.
E368779 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: EPUB | Statement: [Project Gutenberg, fileFormat, EPUB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EPUB
Context triple: [Project Gutenberg, fileFormat, EPUB]
  • A. KPUB
    KPUB is the ICAO airport code for Pueblo Memorial Airport, a public airport serving Pueblo, Colorado, in the United States.
  • B. Kobo e-readers
    Kobo e-readers are a line of digital reading devices known for their wide format support, integration with public libraries, and openness compared to many competing platforms.
  • C. Kindle
    Kindle is Amazon’s line of portable e-readers designed primarily for reading digital books and other electronic publications.
  • D. Rocket eBook at NuvoMedia
    Rocket eBook at NuvoMedia was one of the first commercially produced handheld electronic book readers, co-developed by engineer and entrepreneur Marc Tarpenning in the late 1990s.
  • E. Nook e-reader
    The Nook e-reader is Barnes & Noble’s line of electronic reading devices designed for purchasing, downloading, and reading digital books and other publications.
  • 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: EPUB
Triple: [Project Gutenberg, fileFormat, EPUB]
Generated description
EPUB is a widely used open e-book file format designed for reflowable digital publications that can adapt to different screen sizes and devices.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: EPUB
Target entity description: EPUB is a widely used open e-book file format designed for reflowable digital publications that can adapt to different screen sizes and devices.
  • A. KPUB
    KPUB is the ICAO airport code for Pueblo Memorial Airport, a public airport serving Pueblo, Colorado, in the United States.
  • B. Kobo e-readers
    Kobo e-readers are a line of digital reading devices known for their wide format support, integration with public libraries, and openness compared to many competing platforms.
  • C. Kindle
    Kindle is Amazon’s line of portable e-readers designed primarily for reading digital books and other electronic publications.
  • D. Rocket eBook at NuvoMedia
    Rocket eBook at NuvoMedia was one of the first commercially produced handheld electronic book readers, co-developed by engineer and entrepreneur Marc Tarpenning in the late 1990s.
  • E. Nook e-reader
    The Nook e-reader is Barnes & Noble’s line of electronic reading devices designed for purchasing, downloading, and reading digital books and other publications.
  • 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_69ad85d512708190829c8b2d3a2ccfb8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0c32624819097a96b3d62e3d8f0 completed March 8, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bbbcf2d08190901049948df66f0c completed March 13, 2026, 7:24 a.m.
NEDg Description generation batch_69b3bca07cac81908253b2b4225f3d67 completed March 13, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_69b3f5b6e66c81908700d5f3df0a864d completed March 13, 2026, 11:32 a.m.
Created at: March 8, 2026, 3:21 p.m.