Triple
T24085648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Plum Point Bend |
E596635
|
entity |
| Predicate | involvedVesselType |
P11978
|
FINISHED |
| Object | Confederate rams |
—
|
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: Confederate rams | Statement: [Battle of Plum Point Bend, involvedVesselType, Confederate rams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedVesselType Context triple: [Battle of Plum Point Bend, involvedVesselType, Confederate rams]
-
A.
affectedVessel
Indicates that a vessel is impacted, influenced, or acted upon by a specified event, condition, or process.
-
B.
primaryVessels
Indicates that the related vessels are the main or principal ones within a given system, structure, or context.
-
C.
hasVesselType
chosen
Indicates that an entity is associated with or classified by a specific type of vessel (e.g., ship, boat, or container).
-
D.
usesVesselType
Indicates that an entity performs an activity or operation by employing a specific type or category of vessel.
-
E.
hasVessel
Indicates that one entity possesses, uses, or is associated with a particular vessel (such as a container, ship, or transport medium) in the context of the described relationship or action.
- 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_69e288c4638c81909bacc28a1e3d436b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dc28a7cc81909c76d9d992ac21dc |
completed | April 29, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 10:44 p.m.