Triple

T14343825
Position Surface form Disambiguated ID Type / Status
Subject Java servlets E355663 entity
Predicate usedWith P4791 FINISHED
Object JSTL E736228 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: JSTL | Statement: [Java servlets, usedWith, JSTL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: JSTL
Context triple: [Java servlets, usedWith, JSTL]
  • A. JSP
    JSP is the commonly used abbreviation for the Japan Socialist Party, a former major left-wing political party in Japan.
  • B. Jakarta Standard Tag Library chosen
    Jakarta Standard Tag Library is a collection of reusable JSP tags that simplify common web development tasks such as iteration, conditionals, internationalization, and database access in Java-based web applications.
  • C. Jakarta Server Pages
    Jakarta Server Pages is a Jakarta EE web technology that enables developers to create dynamic, server-side HTML content using Java-based templates.
  • D. Jakarta Expression Language
    Jakarta Expression Language is a Java-based expression language used in Jakarta EE to simplify access to application data and logic within web and enterprise components.
  • E. Facelets
    Facelets is a powerful view declaration language for building component-based user interfaces in Java web applications, particularly with Jakarta Server Faces.
  • 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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8e89ed9c8190acdb647ee618e919 completed April 14, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd469d899081909103563f209dd944 completed May 8, 2026, 2:12 a.m.
Created at: April 10, 2026, 1:14 a.m.