Triple
T10327473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SM U-9 |
E242795
|
entity |
| Predicate | victoryType |
P6374
|
FINISHED |
| Object | Submarine torpedo attack |
—
|
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: Submarine torpedo attack | Statement: [SM U-9, victoryType, Submarine torpedo attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: victoryType Context triple: [SM U-9, victoryType, Submarine torpedo attack]
-
A.
typeOfVictory
chosen
Indicates the specific manner or category in which a victory was achieved.
-
B.
victoryIn
Indicates that one entity achieves a win or success in a specific contest, event, or competitive context involving another entity.
-
C.
conditionOfVictory
Indicates the specific circumstances or criteria under which a participant is considered to have won.
-
D.
victoriousSide
Indicates which participant or group emerged as the winner in a competitive or conflict situation.
-
E.
victoryTarget
Indicates that one entity is the intended opponent, objective, or condition that must be overcome or achieved for the other entity to attain victory.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7cf21e08190bf605daeea0d9dcf |
completed | April 7, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69d4d1f64a648190a79980d647898eb0 |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:51 a.m.