Triple
T7248187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air raid on Bari |
E156528
|
entity |
| Predicate | shipLosses |
P821
|
FINISHED |
| Object | over 15 Allied ships sunk |
—
|
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: over 15 Allied ships sunk | Statement: [Air raid on Bari, shipLosses, over 15 Allied ships sunk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shipLosses Context triple: [Air raid on Bari, shipLosses, over 15 Allied ships sunk]
-
A.
shipsSunkOrTotalLoss
chosen
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
B.
fleetDestroyedBy
Indicates that a fleet was destroyed as a direct result of actions taken by another specified entity.
-
C.
battleshipsDamaged
Indicates that one or more battleships have sustained damage, typically as a result of combat or hostile action.
-
D.
aircraftLosses
Indicates the number or occurrence of aircraft that have been destroyed, damaged beyond repair, or otherwise lost.
-
E.
hasShipwrecks
Indicates that one entity contains, includes, or is associated with shipwrecks located within it or under its control.
- 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_69c68827b5e481908dc05e145b2c92d4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea763f208190af1210cd8d2a05c9 |
completed | March 27, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69c6e7666ffc81908bf643d8257e6337 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:56 p.m.