Triple
T13848293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of the Basque Roads |
E332865
|
entity |
| Predicate | FrenchShipsLostOrGrounded |
P821
|
FINISHED |
| Object | several ships of the line |
—
|
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: several ships of the line | Statement: [Battle of the Basque Roads, FrenchShipsLostOrGrounded, several ships of the line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FrenchShipsLostOrGrounded Context triple: [Battle of the Basque Roads, FrenchShipsLostOrGrounded, several ships of the line]
-
A.
FrenchShips
Indicates that the ships involved are associated with France, typically by nationality, registration, or operation under the French flag.
-
B.
FrenchShipsOfTheLineEngaged
Indicates that French ships of the line were actively involved in a naval engagement or battle.
-
C.
shipsSunkOrTotalLoss
chosen
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
D.
notableShip
Indicates that there is a notable or significant ship associated with the subject entity.
-
E.
FranceCaptain
Indicates that an entity serves as the captain (leader) of a French national or representative team in a given context.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02b2a9788190b164760adec64ef6 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc8691b608190a25a7c70a366b170 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:14 p.m.