Triple
T13633590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Matabele |
E325786
|
entity |
| Predicate | sunkInContextOf |
P102958
|
FINISHED |
| Object | Arctic convoy operations |
—
|
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: Arctic convoy operations | Statement: [HMS Matabele, sunkInContextOf, Arctic convoy operations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sunkInContextOf Context triple: [HMS Matabele, sunkInContextOf, Arctic convoy operations]
-
A.
sinkingContext
chosen
Indicates a context or situation in which something is in the process of sinking, declining, or being submerged.
-
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.
sunkAsTarget
Indicates that an entity was sunk specifically in the role of being a target (e.g., during testing, training, or as a deliberate target in an operation).
-
E.
sunkOff
Indicates that one entity was sunk at a location situated off (near but not directly at) another referenced place or feature.
- 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_69d8076beddc8190a53156f5bea77f5e |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc60635d08190899806fe8936f02a |
completed | April 12, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69dbbe85e1c4819095194f4b7f9f6118 |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:51 p.m.