Triple
T2229358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Class A airspace |
E48727
|
entity |
| Predicate | surveillance |
P25170
|
FINISHED |
| Object | radar-based ATC separation |
—
|
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: radar-based ATC separation | Statement: [Class A airspace, surveillance, radar-based ATC separation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surveillance Context triple: [Class A airspace, surveillance, radar-based ATC separation]
-
A.
securityAgency
Indicates that one entity functions as a security agency responsible for protection, surveillance, or enforcement activities in relation to another entity.
-
B.
hasCCTV
Indicates that one entity is equipped with or monitored by a CCTV (closed-circuit television) system installed or provided by another entity.
-
C.
oversightFocus
chosen
Indicates that one entity’s oversight, supervision, or monitoring activities are specifically directed toward another entity or aspect.
-
D.
security
Indicates that an entity provides protection, safety measures, or safeguards to another entity or against specific threats or risks.
-
E.
surveys
Indicates that one entity systematically examines, questions, or assesses another entity or a situation to gather information or evaluate its state.
- 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_69a88aa51b388190949868ec9766e587 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0685b688190857a76c1043f4b92 |
completed | March 7, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69abbdadbb0c8190b3a1ede31b8acbfa |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.