Triple
T10019661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jakarta Batch |
E200581
|
entity |
| Predicate | originatedAs |
P1257
|
FINISHED |
| Object | JSR 352: Batch Applications for the Java Platform |
E200581
|
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: JSR 352: Batch Applications for the Java Platform | Statement: [Jakarta Batch, originatedAs, JSR 352: Batch Applications for the Java Platform]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: JSR 352: Batch Applications for the Java Platform Context triple: [Jakarta Batch, originatedAs, JSR 352: Batch Applications for the Java Platform]
-
A.
Jakarta Batch
chosen
Jakarta Batch is a Jakarta EE specification that defines a standardized framework for batch processing of large-volume, non-interactive jobs in Java enterprise applications.
-
B.
Jakarta Transactions
Jakarta Transactions is the Jakarta EE specification that defines a standard API and infrastructure for managing distributed transactions in Java enterprise applications.
-
C.
Jakarta Enterprise Beans
Jakarta Enterprise Beans is a Jakarta EE server-side component architecture that simplifies the development of transactional, secure, and scalable business logic in Java enterprise applications.
-
D.
Apache Gobblin
Apache Gobblin is an open-source distributed data integration framework designed for large-scale data ingestion, replication, and lifecycle management across diverse data sources and sinks.
-
E.
Patterns of Enterprise Application Architecture
Patterns of Enterprise Application Architecture is a seminal software engineering book that catalogs and explains common design patterns and best practices for building large-scale enterprise applications.
- 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_69ca831c45f08190ac1505cc15076608 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd4f3a988190892cc698109be8b8 |
completed | April 2, 2026, 1:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26aaa38188190aed8c18eccd8a79d |
completed | April 5, 2026, 1:59 p.m. |
Created at: March 30, 2026, 8:53 p.m.