Triple
T18567788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Non-commissioned officer schools (Imperial Japanese Army) |
E453798
|
entity |
| Predicate | rankOutcome |
P34755
|
FINISHED |
| Object | corporal |
—
|
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: corporal | Statement: [Non-commissioned officer schools (Imperial Japanese Army), rankOutcome, corporal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankOutcome Context triple: [Non-commissioned officer schools (Imperial Japanese Army), rankOutcome, corporal]
-
A.
rankingType
Indicates the specific basis or method by which items are ordered or ranked relative to one another.
-
B.
rankEquivalent
Indicates that two entities hold the same rank or hierarchical level within a given ordering or classification system.
-
C.
rankingScope
Indicates the context or domain within which a ranking is defined, interpreted, or applied.
-
D.
rankStatus
chosen
Indicates the hierarchical level or position an entity holds within an ordered ranking or status system.
-
E.
rankMayVaryBy
Indicates that the rank or ordering associated with something can change depending on specified conditions, contexts, or criteria.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53affc3e08190b4d16b5ccb0bddbc |
completed | April 19, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69e478c16e0c8190b03966aa23c395a6 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:43 a.m.