Triple
T25310840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MAC-in-MAC |
E634602
|
entity |
| Predicate | addsHeaderType |
P158375
|
FINISHED |
| Object | backbone MAC addresses (B‑SA and B‑DA) |
—
|
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: backbone MAC addresses (B‑SA and B‑DA) | Statement: [MAC-in-MAC, addsHeaderType, backbone MAC addresses (B‑SA and B‑DA)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addsHeaderType Context triple: [MAC-in-MAC, addsHeaderType, backbone MAC addresses (B‑SA and B‑DA)]
-
A.
addsHeaderType
chosen
Indicates that one entity appends or associates a specific header type to another entity, such as a message, request, or data structure.
-
B.
addsContentType
Indicates that one entity augments or associates another entity with a specific content type.
-
C.
belongsToHeader
Indicates that something is associated with, contained within, or conceptually grouped under a specific header.
-
D.
addsCardType
Indicates that one entity introduces or associates a specific card type with another entity or collection.
-
E.
addsFeatureType
Indicates that one entity introduces or incorporates a specific feature type into another entity or system.
- 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_69e75a972c6481909bc11710e8d30a6c |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4939e84dc8190bef761d9bfee08a6 |
completed | May 1, 2026, 11:50 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:26 p.m.