Triple
T27591200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Envoy |
E699791
|
entity |
| Predicate | observabilityExport |
P20345
|
FINISHED |
| Object | Prometheus metrics |
—
|
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: Prometheus metrics | Statement: [Envoy, observabilityExport, Prometheus metrics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observabilityExport Context triple: [Envoy, observabilityExport, Prometheus metrics]
-
A.
observability
Indicates that the internal state or behavior of a system can be inferred or monitored through its external outputs or measurements.
-
B.
observedVia
chosen
Indicates that something is perceived, detected, or measured through a particular medium, instrument, method, or channel.
-
C.
observedAs
Indicates that one entity is perceived, recorded, or identified in the role, state, or form of another entity.
-
D.
monitoringOutput
Indicates that one entity observes, records, or tracks the performance, behavior, or results produced by another entity or process.
-
E.
isDirectlyObservable
Indicates that the subject can be perceived or measured directly without inference or intermediate interpretation.
- 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_69ef6a4d71f081909a1235763206b691 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f65a6c900881908f18b61273d7bf8d |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f659ce58408190ba9e007b4810d4d0 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 27, 2026, 2:05 p.m.