Triple
T24575271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | sinking of the German battleship Scharnhorst |
E608085
|
entity |
| Predicate | countryOfShipSunk |
P156397
|
FINISHED |
| Object | Nazi Germany |
—
|
NE NERFINISHED |
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: Nazi Germany | Statement: [sinking of the German battleship Scharnhorst, countryOfShipSunk, Nazi Germany]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfShipSunk Context triple: [sinking of the German battleship Scharnhorst, countryOfShipSunk, Nazi Germany]
-
A.
sunkCountry
Indicates that one entity (typically a vessel or force) caused the sinking of a country’s ship(s) or naval assets belonging to another country.
-
B.
countryOfBritishShips
Indicates the country to which British ships belong or are registered.
-
C.
navalCountry
Indicates that a country possesses or operates a navy, signifying its involvement in naval or maritime military activities.
-
D.
homeportCountry
Indicates the country where a vessel is officially registered as its home port.
-
E.
nationalityOfVessels
Indicates the country or flag state to which vessels legally belong or are registered.
- 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_69e2c4cdab6c8190aae6e5d3de55c95e |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a928896c8190af385755b1418ba6 |
completed | April 30, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69f2a6c1f07081908edf0b521767e79b |
completed | April 30, 2026, 12:48 a.m. |
| PDg | Predicate description generation | batch_69f2a846c5bc81909ba50cee483bea91 |
completed | April 30, 2026, 12:54 a.m. |
Created at: April 18, 2026, 2:29 a.m.