Triple
T17559390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Global Enqueue Service |
E427659
|
entity |
| Predicate | typeOfLocking |
P34001
|
FINISHED |
| Object | global enqueue-based locking |
—
|
LITERAL 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: global enqueue-based locking | Statement: [Global Enqueue Service, typeOfLocking, global enqueue-based locking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfLocking Context triple: [Global Enqueue Service, typeOfLocking, global enqueue-based locking]
-
A.
lockType
chosen
Indicates the specific kind or category of locking mechanism or access restriction applied to an entity or resource.
-
B.
hasLockType
Indicates that an entity is associated with or uses a specific type or category of lock.
-
C.
lockedMeans
Indicates that one state, condition, or action guarantees or necessitates another, such that when the first is "locked in," the second must follow.
-
D.
usesLockSystem
Indicates that one entity employs or relies on a locking mechanism or lock-based system provided by another entity.
-
E.
requiresLock
Indicates that performing the associated action or accessing the related resource is contingent on acquiring a lock to ensure exclusive or synchronized use.
- F. None of above.
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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4562573e48190a19f30fe915a5455 |
completed | April 19, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fb39948190a82a597c5bac5c57 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.