Triple
T411426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Cossack |
E9496
|
entity |
| Predicate | sank |
P3147
|
FINISHED |
| Object | 27 October 1941 |
—
|
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: 27 October 1941 | Statement: [HMS Cossack, sank, 27 October 1941]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sank Context triple: [HMS Cossack, sank, 27 October 1941]
-
A.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
-
B.
placeOfSinking
Indicates the location where an object or entity sank or was submerged.
-
C.
sunkCountry
Indicates that one entity (typically a vessel or force) caused the sinking of a country’s ship(s) or naval assets belonging to another country.
-
D.
dateOfSinking
chosen
Indicates the specific calendar date on which an entity (typically a vessel or structure) sank.
-
E.
wreckDiscovery
Indicates that an entity discovers, finds, or identifies a wreck (such as a ruined or destroyed object, vehicle, or structure).
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ed31681c8190ac32334562fb17fd |
completed | Feb. 28, 2026, 1:27 p.m. |
| PD | Predicate disambiguation | batch_69a2e9737694819080fde9adcc1aa4d4 |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:09 p.m.