Triple
T8950015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Drepanum |
E213320
|
entity |
| Predicate | RomanShipsLost |
P821
|
FINISHED |
| Object | approximately 90 ships captured or 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: approximately 90 ships captured or sunk | Statement: [Battle of Drepanum, RomanShipsLost, approximately 90 ships captured or sunk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RomanShipsLost Context triple: [Battle of Drepanum, RomanShipsLost, approximately 90 ships captured or sunk]
-
A.
shipsSunkOrTotalLoss
chosen
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
B.
numberOfShipwrecks
Indicates the quantity of shipwrecks associated with a given entity or context.
-
C.
sankOnMaidenVoyage
Indicates that the subject vessel sank during its very first voyage.
-
D.
hasShipwrecks
Indicates that one entity contains, includes, or is associated with shipwrecks located within it or under its control.
-
E.
shipwreckEvent
Indicates an event in which a ship is destroyed, stranded, or severely damaged, typically resulting in loss or abandonment at sea or near a shoreline.
- 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_69ca839843408190a39069a029a89f15 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc670b5f50819080f1c73992fe5281 |
completed | April 1, 2026, 12:30 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed5267c8190a43feb2a2f3df1ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 6:59 p.m.