Triple

T2313772
Position Surface form Disambiguated ID Type / Status
Subject Yukihiro Matsumoto E51015 entity
Predicate employer P7 FINISHED
Object Heroku
Heroku is a cloud platform as a service (PaaS) that enables developers to build, run, and scale applications without managing underlying infrastructure.
 E255524 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: Heroku | Statement: [Yukihiro Matsumoto, employer, Heroku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heroku
Context triple: [Yukihiro Matsumoto, employer, Heroku]
  • A. Loudcloud
    Loudcloud was a pioneering early-2000s cloud and managed hosting company co-founded by Marc Andreessen that later evolved into the software firm Opsware.
  • B. Cloudflare
    Cloudflare is a web infrastructure and security company best known for its global content delivery network (CDN), DDoS protection, and DNS services that help improve the performance and security of websites and internet applications.
  • C. New Relic
    New Relic is a software analytics and application performance monitoring company that provides tools for tracking and optimizing the performance of web and mobile applications.
  • D. cloud.gov platform
    cloud.gov platform is a U.S. government-managed cloud hosting and deployment service designed to help federal agencies build, run, and maintain compliant web applications and digital services.
  • E. 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.
  • 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: Heroku
Triple: [Yukihiro Matsumoto, employer, Heroku]
Generated description
Heroku is a cloud platform as a service (PaaS) that enables developers to build, run, and scale applications without managing underlying infrastructure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heroku
Target entity description: Heroku is a cloud platform as a service (PaaS) that enables developers to build, run, and scale applications without managing underlying infrastructure.
  • A. Loudcloud
    Loudcloud was a pioneering early-2000s cloud and managed hosting company co-founded by Marc Andreessen that later evolved into the software firm Opsware.
  • B. Cloudflare
    Cloudflare is a web infrastructure and security company best known for its global content delivery network (CDN), DDoS protection, and DNS services that help improve the performance and security of websites and internet applications.
  • C. New Relic
    New Relic is a software analytics and application performance monitoring company that provides tools for tracking and optimizing the performance of web and mobile applications.
  • D. cloud.gov platform
    cloud.gov platform is a U.S. government-managed cloud hosting and deployment service designed to help federal agencies build, run, and maintain compliant web applications and digital services.
  • E. 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.
  • 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_69a88b074b908190ae983dbca7757d88 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc61c1ef08190911d5f58c2e91189 completed March 7, 2026, 6:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae895f5420819087b403e9772dce9a completed March 9, 2026, 8:48 a.m.
NEDg Description generation batch_69ae8af65eb88190b17d74e7411967cc completed March 9, 2026, 8:55 a.m.
NED2 Entity disambiguation (via description) batch_69ae8ba02cec8190917c0e17d3fedb0e completed March 9, 2026, 8:58 a.m.
Created at: March 4, 2026, 7:49 p.m.