Triple
T7054081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IEEE 802.1ad |
E164040
|
entity |
| Predicate | introducesField |
P33246
|
FINISHED |
| Object | S-TAG |
—
|
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: S-TAG | Statement: [IEEE 802.1ad, introducesField, S-TAG]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducesField Context triple: [IEEE 802.1ad, introducesField, S-TAG]
-
A.
definesField
chosen
Indicates that one entity specifies or declares a particular field or attribute that belongs to or characterizes another entity.
-
B.
fieldIntroduced
Indicates that a particular field or attribute was newly added or introduced into a data structure, schema, or record.
-
C.
introduced
Indicates that one entity caused another entity to become known, presented, or brought into use for the first time to a person, group, or context.
-
D.
supportsField
Indicates that one entity provides the necessary structure, stability, or backing for a particular field, area, or domain associated with another entity.
-
E.
canIntroduce
Indicates that one entity has the ability or permission to introduce another entity to a third party or context.
- 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_69c68861678881909961ddf4d779f750 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e4a3c36c819080942c59f1830ae8 |
completed | March 27, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69c6e1bdc1f08190975fcdbbb1854d1e |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:37 p.m.