Triple
T21662781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bismarck-class battleship |
E534633
|
entity |
| Predicate | fateOfSecondShip |
P144907
|
FINISHED |
| Object | Tirpitz sunk in 1944 |
—
|
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: Tirpitz sunk in 1944 | Statement: [Bismarck-class battleship, fateOfSecondShip, Tirpitz sunk in 1944]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fateOfSecondShip Context triple: [Bismarck-class battleship, fateOfSecondShip, Tirpitz sunk in 1944]
-
A.
secondShip
Indicates that one entity is the second ship in an ordered sequence or ranking relative to another entity.
-
B.
notableVictimShip
Indicates that a ship is recognized as a particularly significant or noteworthy victim in a specific incident or context.
-
C.
burnedShip
Indicates that one entity intentionally set fire to and burned a ship belonging to or associated with another entity.
-
D.
capturedShip
Indicates that one party has taken control of another party's ship, typically by force or seizure.
-
E.
fateOfComponentShip
Indicates the outcome or final status that befalls a component of a ship within the described context or event.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef6c0956e0819093b4794418efe052 |
completed | April 27, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69e696826c3c81909270791e79760937 |
completed | April 20, 2026, 9:11 p.m. |
| PDg | Predicate description generation | batch_69e69b4aa2b48190830107391e81571a |
completed | April 20, 2026, 9:31 p.m. |
Created at: April 16, 2026, 6:36 p.m.