Triple
T18256021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GHC |
E437224
|
entity |
| Predicate | hasFeature |
P182
|
FINISHED |
| Object | Software Transactional Memory |
—
|
NE NERFINISHED |
How this triple was built (3 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: Software Transactional Memory | Statement: [GHC, hasFeature, Software Transactional Memory]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Software Transactional Memory Context triple: [GHC, hasFeature, Software Transactional Memory]
-
A.
The Theory of Database Concurrency Control
The Theory of Database Concurrency Control is a foundational book in computer science that rigorously analyzes the principles and algorithms ensuring correct and efficient concurrent access to databases.
-
B.
Verification of Concurrent Programs
"Verification of Concurrent Programs" is a foundational computer science text that presents formal methods and techniques for proving the correctness of programs that execute concurrently.
-
C.
Concurrency control in distributed database systems
"Concurrency control in distributed database systems" is a seminal work in computer science that systematically analyzes techniques for ensuring correct and efficient transaction processing across distributed databases.
-
D.
Cilk work-stealing scheduler
The Cilk work-stealing scheduler is a parallel runtime scheduling algorithm that efficiently balances dynamic multithreaded workloads by having idle processors "steal" tasks from busy ones, enabling scalable performance on multicore systems.
-
E.
Automatic Storage Management
Automatic Storage Management is Oracle's integrated volume manager and file system that simplifies and optimizes the management of database storage.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Software Transactional Memory Target entity description: Software Transactional Memory is a concurrency control mechanism that lets programmers manage shared memory using atomic transactions instead of explicit locks, simplifying the writing of correct concurrent programs.
-
A.
The Theory of Database Concurrency Control
The Theory of Database Concurrency Control is a foundational book in computer science that rigorously analyzes the principles and algorithms ensuring correct and efficient concurrent access to databases.
-
B.
Verification of Concurrent Programs
"Verification of Concurrent Programs" is a foundational computer science text that presents formal methods and techniques for proving the correctness of programs that execute concurrently.
-
C.
Concurrency control in distributed database systems
"Concurrency control in distributed database systems" is a seminal work in computer science that systematically analyzes techniques for ensuring correct and efficient transaction processing across distributed databases.
-
D.
Cilk work-stealing scheduler
The Cilk work-stealing scheduler is a parallel runtime scheduling algorithm that efficiently balances dynamic multithreaded workloads by having idle processors "steal" tasks from busy ones, enabling scalable performance on multicore systems.
-
E.
Automatic Storage Management
Automatic Storage Management is Oracle's integrated volume manager and file system that simplifies and optimizes the management of database storage.
- F. None of above. chosen
Provenance (2 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4fd85ee548190a102611fcf709ad4 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 10:34 a.m.