Triple

T13019877
Position Surface form Disambiguated ID Type / Status
Subject TImage E322644 entity
Predicate supportsGraphicClass P32439 FINISHED
Object TMetafile
TMetafile is a Delphi graphics class that represents and handles Windows metafile images, allowing scalable, vector-based drawing to be stored and rendered.
E1014704 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: TMetafile | Statement: [TImage, supportsGraphicClass, TMetafile]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TMetafile
Context triple: [TImage, supportsGraphicClass, TMetafile]
  • A. TImage
    TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
  • B. TFile
    TFile is a ROOT framework class that provides an interface for creating, reading, and writing ROOT data files used in high-energy physics and data analysis.
  • C. TIF
    TIF is the former New York Stock Exchange ticker symbol for Tiffany & Co., the luxury jewelry and specialty retailer.
  • D. TIF
    TIF is the IATA airport code for Taif Regional Airport, which serves the city of Taif in Saudi Arabia.
  • E. TIF
    TIF is a major annual international trade fair held in Thessaloniki, Greece, showcasing products, services, and innovations from domestic and global exhibitors.
  • 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: TMetafile
Triple: [TImage, supportsGraphicClass, TMetafile]
Generated description
TMetafile is a Delphi graphics class that represents and handles Windows metafile images, allowing scalable, vector-based drawing to be stored and rendered.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TMetafile
Target entity description: TMetafile is a Delphi graphics class that represents and handles Windows metafile images, allowing scalable, vector-based drawing to be stored and rendered.
  • A. TImage
    TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
  • B. TFile
    TFile is a ROOT framework class that provides an interface for creating, reading, and writing ROOT data files used in high-energy physics and data analysis.
  • C. TIF
    TIF is the IATA airport code for Taif Regional Airport, which serves the city of Taif in Saudi Arabia.
  • D. TIF
    TIF is the former New York Stock Exchange ticker symbol for Tiffany & Co., the luxury jewelry and specialty retailer.
  • E. TIF
    TIF is a major annual international trade fair held in Thessaloniki, Greece, showcasing products, services, and innovations from domestic and global exhibitors.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d9804b743c8190810dc5c14bc6d912 completed April 10, 2026, 10:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c116423881908d0de1e04904fbc3 completed May 3, 2026, 3:29 a.m.
NEDg Description generation batch_69f6c20aff008190a1a10ac02ed08726 completed May 3, 2026, 3:33 a.m.
NED2 Entity disambiguation (via description) batch_69f6c2de143c81908164f5df2b92e5c3 completed May 3, 2026, 3:37 a.m.
Created at: April 9, 2026, 8:51 p.m.