Triple
T8121093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German battleship Bismarck |
E189608
|
entity |
| Predicate | rudderDisabledBy |
P81383
|
FINISHED |
| Object | aerial torpedo hit |
—
|
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: aerial torpedo hit | Statement: [German battleship Bismarck, rudderDisabledBy, aerial torpedo hit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rudderDisabledBy Context triple: [German battleship Bismarck, rudderDisabledBy, aerial torpedo hit]
-
A.
disabledByDefaultIn
Indicates that a feature, capability, or setting is turned off by default within the specified context or environment.
-
B.
canBeDisabledOn
Indicates that a feature, function, or capability has the property that it can be turned off or deactivated when applied to the referenced entity.
-
C.
cannotBeEasilyDisabled
Indicates that the relationship or mechanism cannot be turned off, bypassed, or neutralized without significant effort, expertise, or resources.
-
D.
replacedWhenDisabledBy
Indicates that when one entity becomes disabled or nonfunctional, it is substituted or taken over by another entity.
-
E.
isNotedByPilotsAs
Indicates that something is recognized, remarked upon, or specifically mentioned by pilots.
- F. None of above. chosen
Provenance (4 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_69ca82bb74848190afb1f18640632c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4664fef881908b0dc7b158aca398 |
completed | March 31, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69cb368e7f4c81909aabd7716f0de79d |
completed | March 31, 2026, 2:50 a.m. |
| PDg | Predicate description generation | batch_69cb46635424819085d086972b264280 |
completed | March 31, 2026, 3:58 a.m. |
Created at: March 30, 2026, 5:33 p.m.