Triple
T16412372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russian battleship Petropavlovsk |
E398597
|
entity |
| Predicate | sankAfter |
P18834
|
FINISHED |
| Object | striking Japanese-laid mines |
—
|
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: striking Japanese-laid mines | Statement: [Russian battleship Petropavlovsk, sankAfter, striking Japanese-laid mines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sankAfter Context triple: [Russian battleship Petropavlovsk, sankAfter, striking Japanese-laid mines]
-
A.
sankOn
Indicates that one entity moved downward and became submerged or lower in level relative to another entity or reference point.
-
B.
sunkAs
Indicates that one entity caused another entity to sink or become submerged, typically resulting in its loss or destruction.
-
C.
sunk
Indicates that one entity caused another entity to go below the surface of a liquid, typically water, so that it is submerged or destroyed.
-
D.
sunkDuring
chosen
Indicates that one entity was sunk in the course of, or as a result of, the event or time period represented by another entity.
-
E.
sankWhileNamed
Indicates that an entity sank at a time when it bore a particular name.
- 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_69d87f2950248190bc8ad9b9bebdc8c8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32874a0cc8190874aea10b1d13004 |
completed | April 18, 2026, 6:45 a.m. |
| PD | Predicate disambiguation | batch_69e226fe1dd08190865c181721f8c348 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:09 a.m.