Triple

T452075
Position Surface form Disambiguated ID Type / Status
Subject Microsoft 365 E7151 entity
Predicate includes P1393 FINISHED
Object Word
Word is Microsoft’s widely used word processing application for creating, editing, and formatting text documents.
 E56704 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: Word | Statement: [Microsoft 365, includes, Word]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Word
Context triple: [Microsoft 365, includes, Word]
  • A. PowerPoint
    PowerPoint is a widely used Microsoft presentation software application for creating, editing, and delivering slide-based visual presentations.
  • B. MacWrite
    MacWrite was one of the first WYSIWYG word processors for the original Macintosh, showcasing the platform’s graphical user interface and desktop publishing capabilities.
  • C. TextEdit
    TextEdit is a simple, built-in macOS application for creating and editing plain text and rich text documents.
  • D. Google Docs
    Google Docs is a cloud-based word processing application by Google that allows users to create, edit, and collaborate on documents in real time through a web browser or mobile app.
  • E. docuverse
    Docuverse is Ted Nelson’s visionary concept of a universal, interconnected digital library where all documents are permanently linked and traceable across a global hypertext system.
  • 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: Word
Triple: [Microsoft 365, includes, Word]
Generated description
Word is Microsoft’s widely used word processing application for creating, editing, and formatting text documents.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Word
Target entity description: Word is Microsoft’s widely used word processing application for creating, editing, and formatting text documents.
  • A. PowerPoint
    PowerPoint is a widely used Microsoft presentation software application for creating, editing, and delivering slide-based visual presentations.
  • B. MacWrite
    MacWrite was one of the first WYSIWYG word processors for the original Macintosh, showcasing the platform’s graphical user interface and desktop publishing capabilities.
  • C. TextEdit
    TextEdit is a simple, built-in macOS application for creating and editing plain text and rich text documents.
  • D. Google Docs
    Google Docs is a cloud-based word processing application by Google that allows users to create, edit, and collaborate on documents in real time through a web browser or mobile app.
  • E. docuverse
    Docuverse is Ted Nelson’s visionary concept of a universal, interconnected digital library where all documents are permanently linked and traceable across a global hypertext system.
  • 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_69a2e7e4676c81909ea0dbdecac0687c completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ef854f7481909dc2207faf0327ec completed Feb. 28, 2026, 1:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69a44802e858819081a0b5b98bb25bce completed March 1, 2026, 2:06 p.m.
NEDg Description generation batch_69a449b1e2708190838e32497ffd2fbd completed March 1, 2026, 2:14 p.m.
NED2 Entity disambiguation (via description) batch_69a44a07fa18819089cb8005d476d078 completed March 1, 2026, 2:15 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.