Triple
T10049843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RFC 903 |
E207717
|
entity |
| Predicate | specifiesMappingFrom |
P9923
|
FINISHED |
| Object | link-layer address |
—
|
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: link-layer address | Statement: [RFC 903, specifiesMappingFrom, link-layer address]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specifiesMappingFrom Context triple: [RFC 903, specifiesMappingFrom, link-layer address]
-
A.
mappedUsing
Indicates that one entity is associated or transformed into another entity through a specified mapping method or mechanism.
-
B.
typicalMapping
Indicates a standard or commonly used correspondence between elements of one set, structure, or representation and those of another.
-
C.
mapsTo
chosen
Indicates that one entity is associated with or transformed into another entity, typically defining a directional correspondence or function from a source to a target.
-
D.
hasOfficialMapping
Indicates that there exists an established, authoritative correspondence or translation between one entity and another.
-
E.
mappingSupportBy
Indicates that one entity provides support, resources, or functionality enabling another entity to perform or maintain a mapping between elements.
- 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_69ca835ad0608190b7c80b292da004f5 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cdcf8e41c4819091fa12742197e207 |
completed | April 2, 2026, 2:08 a.m. |
| PD | Predicate disambiguation | batch_69cd4b8d2280819089de27e57babd1f3 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:56 p.m.