Triple
T403229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bureau of Transportation Statistics |
E9328
|
entity |
| Predicate | dataDomain |
P1248
|
FINISHED |
| Object | aviation |
—
|
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: aviation | Statement: [Bureau of Transportation Statistics, dataDomain, aviation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataDomain Context triple: [Bureau of Transportation Statistics, dataDomain, aviation]
-
A.
regulatoryDomain
Indicates that one entity defines or governs the rules, policies, or constraints under which another entity must operate.
-
B.
usedInDomain
chosen
Indicates that something (such as a concept, method, or resource) is applied or utilized within a particular domain or field.
-
C.
dataUse
Indicates how data is intended to be accessed, processed, or applied within a particular context or activity.
-
D.
secondaryDomain
Indicates that one domain functions as a secondary or auxiliary domain in relation to a primary domain.
-
E.
policyDomain
Indicates the thematic or subject-matter area to which a given policy, rule, or regulatory action belongs.
- 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_69a2e8004cb88190b92ed1add6abf41a |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2eca0e2048190a7bf360257965e56 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e97066e8819083cc1b3a421b9650 |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.