Triple
T8411780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Mylae |
E198640
|
entity |
| Predicate | RomanShipsCapturedOrSunk |
P23911
|
FINISHED |
| Object | about 50 Carthaginian 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: about 50 Carthaginian ships captured or sunk | Statement: [Battle of Mylae, RomanShipsCapturedOrSunk, about 50 Carthaginian ships captured or sunk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RomanShipsCapturedOrSunk Context triple: [Battle of Mylae, RomanShipsCapturedOrSunk, about 50 Carthaginian ships captured or sunk]
-
A.
shipsSunkOrTotalLoss
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
B.
capturedShip
chosen
Indicates that one party has taken control of another party's ship, typically by force or seizure.
-
C.
fleetDestroyedBy
Indicates that a fleet was destroyed as a direct result of actions taken by another specified entity.
-
D.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
-
E.
dispositionOfShips
Indicates the arrangement, allocation, or positioning of ships relative to a plan, location, or situation.
- 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_69ca831201b481909e137936ef99ff11 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb83e0341c819080506e696131671e |
completed | March 31, 2026, 8:20 a.m. |
| PD | Predicate disambiguation | batch_69cb70d473dc8190af8ea81ee5aa970d |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:05 p.m.