Triple
T21224327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ARP (Allocation and Retention Priority) |
E523051
|
entity |
| Predicate | relevantWhen |
P126339
|
FINISHED |
| Object | Network congestion |
—
|
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: Network congestion | Statement: [ARP (Allocation and Retention Priority), relevantWhen, Network congestion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relevantWhen Context triple: [ARP (Allocation and Retention Priority), relevantWhen, Network congestion]
-
A.
relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
-
B.
mayRelateTo
Indicates a possible, but not certain, relationship or association between two entities.
-
C.
conditionRelatesTo
chosen
Indicates that one condition is relevant, connected, or applicable to another condition or contextual factor.
-
D.
relatedTo
Indicates a general, non-specific relationship or association exists between two entities.
-
E.
relatedCorrespondence
Indicates that there exists a piece of correspondence (such as a letter, email, or message) that is associated with or pertains to the related entity.
- 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_69e0b512ad94819087942b2ed925185f |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734a9c9f88190817b574f916886e5 |
completed | April 21, 2026, 8:26 a.m. |
| PD | Predicate disambiguation | batch_69e5f60e1a888190ba75e2e900270a4e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:44 p.m.