Triple
T5463715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embassy of Australia in Washington, D.C. |
E122653
|
entity |
| Predicate | emailDomain |
P5097
|
FINISHED |
| Object | @dfat.gov.au |
—
|
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: @dfat.gov.au | Statement: [Embassy of Australia in Washington, D.C., emailDomain, @dfat.gov.au]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: emailDomain Context triple: [Embassy of Australia in Washington, D.C., emailDomain, @dfat.gov.au]
-
A.
emailAddressDomain
chosen
Indicates that one entity is the domain portion (e.g., "example.com") of another entity’s email address.
-
B.
inputDomain
Indicates that a function, process, or system accepts inputs belonging to a specified domain or set of allowable values.
-
C.
defaultDomain
Indicates that one entity serves as the standard or primary domain associated with another entity, used when no more specific domain is specified.
-
D.
typicalDomain
Indicates that one entity is the characteristic or most common domain, context, or area of application in which another entity typically occurs or is used.
-
E.
publicDomain
Indicates that a work or resource is not protected by intellectual property rights and is freely available for anyone to use, copy, modify, and distribute without restriction.
- 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_69bd4643f16081908d7f29e08096115a |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd927c946c8190aef40679199fede3 |
completed | March 20, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69bd91a370a88190b5d17b8a5387138d |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:08 p.m.