Triple
T10559405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kawasaki Ki-61 |
E249174
|
entity |
| Predicate | resembled |
P35666
|
FINISHED |
| Object | contemporary European fighters |
—
|
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: contemporary European fighters | Statement: [Kawasaki Ki-61, resembled, contemporary European fighters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resembled Context triple: [Kawasaki Ki-61, resembled, contemporary European fighters]
-
A.
resembles
chosen
Indicates that one entity is similar in appearance, form, or characteristics to another.
-
B.
emulates
Indicates that one entity imitates or reproduces the behavior, function, or characteristics of another.
-
C.
materiallySimilarTo
Indicates that two entities share substantially the same physical or material characteristics, composition, or properties, though they may not be exactly identical.
-
D.
lessSimilarTo
Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
-
E.
reversed
Indicates that the direction or order of a previously defined relationship or sequence between entities is inverted.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5271e65688190bcf7931373d87f94 |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d51901ff6c819095e7b528170a69dc |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:35 p.m.