Triple
T3219020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republic of China Air Force |
E67463
|
entity |
| Predicate | usesAirDefenseSystem |
P37495
|
FINISHED |
| Object | surface-to-air missiles |
—
|
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: surface-to-air missiles | Statement: [Republic of China Air Force, usesAirDefenseSystem, surface-to-air missiles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesAirDefenseSystem Context triple: [Republic of China Air Force, usesAirDefenseSystem, surface-to-air missiles]
-
A.
airDefenseSystemInvolved
Indicates that an air defense system participates in or is used during a specific event, operation, or engagement.
-
B.
airDefenseSystem
chosen
Indicates a defensive military system designed to detect, track, and engage airborne threats such as aircraft or missiles.
-
C.
airDefenseSystemComponent
Indicates that one entity is a component or subsystem of an air defense system associated with another entity.
-
D.
usesMissileSystem
Indicates that one entity employs or operates a particular missile system as part of its capabilities or actions.
-
E.
airfieldDefended
Indicates that defensive measures or forces are in place to protect an airfield from attack or unauthorized intrusion.
- 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_69ad858b8adc8190ad989712c87a476b |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adab0c48b481909d1bd9dc41dfa8c2 |
completed | March 8, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0bb6c48190a0659c67d40ee37c |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:08 p.m.