Triple

T1500134
Position Surface form Disambiguated ID Type / Status
Subject Omniture E29776 entity
Predicate acquiredBy P347 FINISHED
Object Adobe E4436 NE FINISHED

How this triple was built (2 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: Adobe | Statement: [Omniture, acquiredBy, Adobe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adobe
Context triple: [Omniture, acquiredBy, Adobe]
  • A. Adobe Inc. chosen
    Adobe Inc. is a multinational software company best known for its creative and multimedia products such as Photoshop, Illustrator, and Acrobat, widely used in digital media and design industries.
  • B. Adobe Creative Cloud
    Adobe Creative Cloud is a subscription-based suite of creative software and services for tasks like graphic design, video editing, web development, and photography.
  • C. Adobe Acrobat
    Adobe Acrobat is a widely used software application for creating, viewing, editing, and managing PDF (Portable Document Format) documents across multiple platforms.
  • D. Macromedia
    Macromedia was a pioneering software company best known for creating web and multimedia tools like Flash and Dreamweaver before being acquired by Adobe.
  • E. Adobe PageMaker
    Adobe PageMaker was one of the first widely used desktop publishing applications, popular in the 1980s and 1990s for creating professional-quality printed documents such as brochures, newsletters, and books.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6f2d7f881909188a3e5614335cd completed March 1, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69adf3b07b688190a0c90796da21c4d5 completed March 8, 2026, 10:09 p.m.
Created at: March 1, 2026, 8:12 p.m.