Triple
T7985459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | YARN |
E185672
|
entity |
| Predicate | roleOfResourceManager |
P56870
|
FINISHED |
| Object | cluster-level resource arbitration |
—
|
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: cluster-level resource arbitration | Statement: [YARN, roleOfResourceManager, cluster-level resource arbitration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfResourceManager Context triple: [YARN, roleOfResourceManager, cluster-level resource arbitration]
-
A.
manager
Indicates that one entity holds a supervisory or administrative role with authority and responsibility over another entity.
-
B.
roleInOperation
chosen
Indicates that an entity holds a specific function, duty, or position within a particular operation or activity.
-
C.
ownerRole
Indicates the role or capacity in which an entity serves as the owner of another entity.
-
D.
systemRole
Indicates the functional position or responsibility that an entity holds within a larger system or structure.
-
E.
regulatorRole
Indicates that one entity serves in an official capacity to oversee, control, or enforce rules and standards governing another entity or activity.
- 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_69ca829a2cfc819083d591d58ec04075 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c4a55b881909a96133e56c0dffa |
completed | March 31, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69cb048009a08190b4c577208a9f8f76 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:15 p.m.