Triple
T20490525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German submarine U-75 |
E502729
|
entity |
| Predicate | sunkShips_type |
P98360
|
FINISHED |
| Object | merchant ships |
—
|
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: merchant ships | Statement: [German submarine U-75, sunkShips_type, merchant ships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sunkShips_type Context triple: [German submarine U-75, sunkShips_type, merchant ships]
-
A.
shipTypeSunk
chosen
Indicates that a particular type of ship has been sunk as a result of some event or action.
-
B.
shipsSunkOrTotalLoss
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
C.
shipwrecksDestroyedIn
Indicates that one or more shipwrecks were destroyed within a specified location or during a particular event or time period.
-
D.
notableVictimShip
Indicates that a ship is recognized as a particularly significant or noteworthy victim in a specific incident or context.
-
E.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cb8e7848190a1dc497a10ae798c |
completed | April 20, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69e59fcdf6e08190a604204615dc56e6 |
completed | April 20, 2026, 3:38 a.m. |
Created at: April 16, 2026, 11:35 a.m.