Triple

T232472
Position Surface form Disambiguated ID Type / Status
Subject Adobe Inc. E4436 entity
Predicate hasSubsidiary P254 FINISHED
Object Behance E29777 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: Behance | Statement: [Adobe Inc., hasSubsidiary, Behance]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Behance
Context triple: [Adobe Inc., hasSubsidiary, Behance]
  • A. Behance chosen
    Behance is an online platform for showcasing and discovering creative work, widely used by designers, artists, and other visual professionals.
  • B. Adobe XD
    Adobe XD is a vector-based user experience design and prototyping tool used to create and test interfaces for websites and mobile applications.
  • C. Theme Building
    The Theme Building is a futuristic, space-age landmark structure at Los Angeles International Airport known for its distinctive flying-saucer design and iconic mid-century modern architecture.
  • D. Automattic
    Automattic is a web development and publishing company best known for owning and operating WordPress.com and several other major online platforms and tools.
  • E. Adobe Stock
    Adobe Stock is Adobe’s royalty-free stock content service offering millions of photos, illustrations, vectors, videos, and other creative assets for use in design and media projects.
  • 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_69a257363ffc81909757bde7ab3404da completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25caf59948190bacac41a6ed84cb6 completed Feb. 28, 2026, 3:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69a36478ebcc8190b95419be9bc6bba3 completed Feb. 28, 2026, 9:56 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.