Triple

T14383903
Position Surface form Disambiguated ID Type / Status
Subject java.net E356674 entity
Predicate containsClass P9272 FINISHED
Object java.net.URL E356674 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: java.net.URL | Statement: [java.net, containsClass, java.net.URL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: java.net.URL
Context triple: [java.net, containsClass, java.net.URL]
  • A. java.net chosen
    java.net is a core Java package that provides classes and interfaces for networking, including support for sockets, URLs, and IP addressing.
  • B. urllib
    urllib is a Python standard library package that provides high-level and low-level interfaces for working with URLs and handling HTTP requests.
  • C. URL (Swift)
    URL (Swift) is a Foundation framework type that represents and manipulates Uniform Resource Locators in a type-safe, structured way within Swift applications.
  • D. Uri
    Uri is a historic Swiss canton in central Switzerland, known as one of the founding members of the Swiss Confederation.
  • E. OpenURL
    OpenURL is a standardized format for creating web links that transport bibliographic and resource metadata between information services to enable context-sensitive linking.
  • 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_69d827927c988190ad98bb0360981783 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de900d28c88190a37feee4743563de completed April 14, 2026, 7:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5511c9e4819089dcbf089ca0dc6a completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:16 a.m.