Triple

T95413
Position Surface form Disambiguated ID Type / Status
Subject HTML E1918 entity
Predicate basedOn P98 FINISHED
Object SGML
SGML (Standard Generalized Markup Language) is a standardized metalanguage for defining markup languages used to structure and describe the content of electronic documents.
E8666 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: SGML | Statement: [HTML, basedOn, SGML]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SGML
Context triple: [HTML, basedOn, SGML]
  • A. XML
    XML (Extensible Markup Language) is a flexible, text-based markup language designed for structuring, storing, and transporting data in a platform-independent way.
  • B. SVG
    SVG (Scalable Vector Graphics) is an XML-based vector image format for two-dimensional graphics that supports interactivity and animation, widely used for web graphics due to its scalability and resolution independence.
  • C. HTML
    HTML (HyperText Markup Language) is the standard markup language used to structure and present content on the World Wide Web.
  • D. SAS
    SAS is the School of Arts and Sciences at the University of Pennsylvania, encompassing the university’s core liberal arts and sciences departments and programs.
  • E. SAS
    SAS is a widely used statistical software suite for advanced analytics, business intelligence, data management, and predictive modeling.
  • 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: SGML
Triple: [HTML, basedOn, SGML]
Generated description
SGML (Standard Generalized Markup Language) is a standardized metalanguage for defining markup languages used to structure and describe the content of electronic documents.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SGML
Target entity description: SGML (Standard Generalized Markup Language) is a standardized metalanguage for defining markup languages used to structure and describe the content of electronic documents.
  • A. XML
    XML (Extensible Markup Language) is a flexible, text-based markup language designed for structuring, storing, and transporting data in a platform-independent way.
  • B. SVG
    SVG (Scalable Vector Graphics) is an XML-based vector image format for two-dimensional graphics that supports interactivity and animation, widely used for web graphics due to its scalability and resolution independence.
  • C. HTML
    HTML (HyperText Markup Language) is the standard markup language used to structure and present content on the World Wide Web.
  • D. SAS
    SAS is the School of Arts and Sciences at the University of Pennsylvania, encompassing the university’s core liberal arts and sciences departments and programs.
  • E. SAS
    SAS is a widely used statistical software suite for advanced analytics, business intelligence, data management, and predictive modeling.
  • 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_69a24d4862f881908cc8b89d3a78031d completed Feb. 28, 2026, 2:04 a.m.
NER Named-entity recognition batch_69a24fd4777c81909ea9b9a6bd4f7ad5 completed Feb. 28, 2026, 2:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69a266ed314881908b6e5e7a91930b56 completed Feb. 28, 2026, 3:54 a.m.
NEDg Description generation batch_69a2677d22cc8190873d775074795a46 completed Feb. 28, 2026, 3:56 a.m.
NED2 Entity disambiguation (via description) batch_69a267e41e148190856aa61cbb0df0ae completed Feb. 28, 2026, 3:58 a.m.
Created at: Feb. 28, 2026, 2:09 a.m.