Triple
T9568714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Иван Кожедуб |
E230856
|
entity |
| Predicate | воинское звание |
P342
|
FINISHED |
| Object | маршал авиации |
—
|
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: маршал авиации | Statement: [Иван Кожедуб, воинское звание, маршал авиации]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: воинское звание Context triple: [Иван Кожедуб, воинское звание, маршал авиации]
-
A.
militaryRank
chosen
Indicates that one entity holds a specific position or level within a hierarchical military ranking system relative to another entity.
-
B.
isMilitaryRank
Indicates that one entity holds a specific position or level within a formal military hierarchy in relation to another.
-
C.
isMilitaryOrderGrade
Indicates that one entity is classified as a specific grade or level within a military order or honor system in relation to another entity.
-
D.
militaryRankBeforeAccession
Indicates the military rank held by an individual prior to their accession to a particular office, position, or status.
-
E.
producedMilitaryRank
Indicates that one entity is responsible for conferring, generating, or resulting in the military rank held by another 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_69ca847f22188190a56e4a97625bef22 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9987cb0c8190af32a1193de54890 |
completed | April 1, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69ccd59b960c8190966a8870a2426bd5 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:04 p.m.