Triple

T82137
Position Surface form Disambiguated ID Type / Status
Subject Microsoft E1649 entity
Predicate acquired P2511 FINISHED
Object GitHub E5697 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: GitHub | Statement: [Microsoft, acquired, GitHub]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GitHub
Context triple: [Microsoft, acquired, GitHub]
  • A. GitHub chosen
    GitHub is a widely used web-based platform for version control and collaborative software development, built around the Git system and popular among open-source and enterprise projects.
  • B. Geeks Bearing Gifts
    Geeks Bearing Gifts is a book by computing pioneer Ted Nelson that reflects on the history, philosophy, and future of digital media and information technology.
  • C. Google
    Google is a multinational technology company best known for its search engine and wide range of internet-related products and services, including Android, YouTube, and cloud computing.
  • D. Red Hat
    Red Hat is a leading American open-source software company best known for its enterprise Linux distribution and related cloud and middleware solutions.
  • E. World Wide Web Foundation
    The World Wide Web Foundation is a nonprofit organization dedicated to advancing an open, accessible, and rights-based web for everyone worldwide.
  • 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_69a24c8150408190910a693eb51c1f71 completed Feb. 28, 2026, 2:01 a.m.
NER Named-entity recognition batch_69a2567c90308190a9b989c586f7e559 completed Feb. 28, 2026, 2:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69a25abdf36c819087c4be57bd8ce8c5 completed Feb. 28, 2026, 3:02 a.m.
Created at: Feb. 28, 2026, 2:06 a.m.