Triple
T11784030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T-29 |
E280223
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | T-29A |
E280223
|
NE 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: T-29A | Statement: [T-29, hasVariant, T-29A]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T-29A Context triple: [T-29, hasVariant, T-29A]
-
A.
T-29
chosen
T-29 is a U.S. Air Force military trainer aircraft variant of the Convair 240 series used primarily for navigation and radar training.
-
B.
T-2 Buckeye
The T-2 Buckeye is an American-built jet trainer aircraft widely used for advanced pilot training, notably by the U.S. Navy and several foreign air forces.
-
C.
TAM medium tank
The TAM medium tank is an Argentine-designed and -produced main battle tank developed in the 1970s to provide the country with a modern, mobile armored fighting vehicle suited to its terrain and military needs.
-
D.
T-34A
The T-34A is the initial production version of the Beechcraft T-34 Mentor, used primarily as a basic piston-engine military trainer aircraft.
-
E.
T-10
T-10 is the station code for Nihonbashi Station on Tokyo Metro’s Tozai Line in central Tokyo.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a585795c8190aa8a5edf0d99b47f |
completed | April 10, 2026, 7:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f090d861f481909b920197a3d60e28 |
completed | April 28, 2026, 10:50 a.m. |
Created at: April 8, 2026, 9:42 p.m.