Triple
T28684052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Husband E. Kimmel |
E726082
|
entity |
| Predicate | rankReducedTo |
P162499
|
FINISHED |
| Object | rear admiral |
—
|
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: rear admiral | Statement: [Husband E. Kimmel, rankReducedTo, rear admiral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankReducedTo Context triple: [Husband E. Kimmel, rankReducedTo, rear admiral]
-
A.
typicalRank
Indicates the usual or most common rank or position an entity holds within a given ordering or hierarchy.
-
B.
typicalRankRange
Indicates the usual or most common range of ranks or ordered positions that an entity typically occupies within a ranking or hierarchy.
-
C.
typicalRankPrefix
Indicates that one entity is a commonly used or standard prefix attached to the rank represented by the other entity.
-
D.
reducedRepresentationOf
Indicates that one entity is a simplified, compressed, or lower-detail version of another entity while preserving its essential information or structure.
-
E.
reductionTo
chosen
Indicates that one entity is transformed, simplified, or mapped into another entity that is considered an equivalent or simpler form, often preserving essential properties.
- 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_69f01d867608819086bc3e6b4f9de866 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6567f9058819085754d42f495f9ec |
completed | May 2, 2026, 7:54 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:11 a.m.