Triple
T21662697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Jamaica |
E534631
|
entity |
| Predicate | roleAtBattleOfNorthCape |
P144905
|
FINISHED |
| Object | fired torpedoes at Scharnhorst |
—
|
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: fired torpedoes at Scharnhorst | Statement: [HMS Jamaica, roleAtBattleOfNorthCape, fired torpedoes at Scharnhorst]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAtBattleOfNorthCape Context triple: [HMS Jamaica, roleAtBattleOfNorthCape, fired torpedoes at Scharnhorst]
-
A.
roleInBattleOfTheChesapeake
Indicates the specific function, position, or involvement an entity had in the Battle of the Chesapeake.
-
B.
roleInBattleOfNavarino
Indicates the specific role or involvement an entity had in the Battle of Navarino.
-
C.
roleAtJutland
Indicates the specific role or position an entity held in relation to the Battle of Jutland.
-
D.
roleInFirstFleet
Indicates that an entity held a specific role or position within the First Fleet.
-
E.
roleInBismarckHunt
Indicates that an entity participated in the historical pursuit of the German battleship Bismarck in a specified role or capacity.
- 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.