Triple
T3291931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMS Lützow |
E69120
|
entity |
| Predicate | scuttlingMethod |
P13566
|
FINISHED |
| Object | torpedoed by German destroyers |
—
|
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: torpedoed by German destroyers | Statement: [SMS Lützow, scuttlingMethod, torpedoed by German destroyers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scuttlingMethod Context triple: [SMS Lützow, scuttlingMethod, torpedoed by German destroyers]
-
A.
finalSinkingMethod
chosen
Indicates the method or process ultimately used to sink or deliberately submerge an object, typically a vessel or structure.
-
B.
reasonForScuttling
Indicates the specific cause or motivation that led to a vessel being deliberately scuttled.
-
C.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
-
D.
torpedoed
Indicates that one entity attacked and struck another entity using a torpedo, typically causing damage or destruction.
-
E.
methodOfDisappearance
Indicates the specific way or process by which an entity ceases to be present, visible, or existent.
- 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_69ad859d45748190b0742408c954b39f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb07379dc8190b7bb409bcf42bdd6 |
completed | March 8, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69ada42407dc81909f60d7a14e1b7934 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:10 p.m.