Triple

T6789955
Position Surface form Disambiguated ID Type / Status
Subject Adobe Photoshop E155906 entity
Predicate fileFormatSupport P8463 FINISHED
Object PNG
PNG (Portable Network Graphics) is a widely used raster image format known for its lossless compression and support for transparency, commonly used for web graphics and digital images.
E618924 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: PNG | Statement: [Adobe Photoshop, fileFormatSupport, PNG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PNG
Context triple: [Adobe Photoshop, fileFormatSupport, PNG]
  • A. PNG
    PNG is the three-letter ISO 3166-1 alpha-3 country code representing Papua New Guinea.
  • B. JPEG
    JPEG is a widely used digital image format that compresses photographic content to reduce file size while maintaining acceptable visual quality.
  • C. PNGRFL
    PNGRFL is the national governing body responsible for organizing and overseeing rugby league in Papua New Guinea.
  • D. PICA format
    PICA format is a library data exchange and cataloging standard widely used in German-speaking countries, particularly in academic and research libraries.
  • E. PSD
    PSD is a major center-right political party in Portugal that has played a leading role in the country’s post-revolution democratic politics and governance.
  • 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: PNG
Triple: [Adobe Photoshop, fileFormatSupport, PNG]
Generated description
PNG (Portable Network Graphics) is a widely used raster image format known for its lossless compression and support for transparency, commonly used for web graphics and digital images.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PNG
Target entity description: PNG (Portable Network Graphics) is a widely used raster image format known for its lossless compression and support for transparency, commonly used for web graphics and digital images.
  • A. PNG
    PNG is the three-letter ISO 3166-1 alpha-3 country code representing Papua New Guinea.
  • B. JPEG
    JPEG is a widely used digital image format that compresses photographic content to reduce file size while maintaining acceptable visual quality.
  • C. PNGRFL
    PNGRFL is the national governing body responsible for organizing and overseeing rugby league in Papua New Guinea.
  • D. PICA format
    PICA format is a library data exchange and cataloging standard widely used in German-speaking countries, particularly in academic and research libraries.
  • E. PSD
    PSD is a major center-right political party in Portugal that has played a leading role in the country’s post-revolution democratic politics and governance.
  • 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_69c6881770fc8190972b2906390380f5 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d2ab4ce88190b6311e4d5aac758c completed March 27, 2026, 6:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c71a8c445c8190abea97a04d648f52 completed March 28, 2026, 12:02 a.m.
NEDg Description generation batch_69c71b186238819096ef6162f9068543 completed March 28, 2026, 12:04 a.m.
NED2 Entity disambiguation (via description) batch_69c71b98b8008190a972cc0a215295c0 completed March 28, 2026, 12:06 a.m.
Created at: March 27, 2026, 2:15 p.m.