Triple
T4958012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kawasaki T-4 |
E111333
|
entity |
| Predicate | nationalRegistrationPrefix |
P7142
|
FINISHED |
| Object | JASDF serial numbers |
—
|
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: JASDF serial numbers | Statement: [Kawasaki T-4, nationalRegistrationPrefix, JASDF serial numbers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nationalRegistrationPrefix Context triple: [Kawasaki T-4, nationalRegistrationPrefix, JASDF serial numbers]
-
A.
civilRegistrationPrefixExample
Indicates that there is an example of a standard prefix used in civil registration identifiers or records.
-
B.
registrationPrefix
chosen
Indicates that an entity has a specific registration prefix code assigned to it as part of its official registration or identification.
-
C.
nationalRegisterStatus
Indicates whether an entity is listed, eligible, or otherwise classified within an official national register or registry.
-
D.
namePrefix
Indicates that one entity is a prefix or leading part of another entity’s name.
-
E.
icaoRegionPrefix
Indicates the regional ICAO prefix that designates the geographic or administrative region associated with an aviation-related entity.
- 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_69bd4418390c8190b7e9766a2512ce55 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd71d834c0819087f3faafdc9b4228 |
completed | March 20, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3beb008190852fd6150813b252 |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:32 p.m.