Triple
T11053606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naval Battle of Lissa |
E261317
|
entity |
| Predicate | ItalianFleetStrength |
P28429
|
FINISHED |
| Object | larger than Austrian fleet |
—
|
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: larger than Austrian fleet | Statement: [Naval Battle of Lissa, ItalianFleetStrength, larger than Austrian fleet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ItalianFleetStrength Context triple: [Naval Battle of Lissa, ItalianFleetStrength, larger than Austrian fleet]
-
A.
ItalianForcesComposition
Indicates the makeup and structure of the Italian military forces involved in a particular context or operation.
-
B.
SpanishFleetStrength
Indicates the relative size or power of a Spanish naval fleet in a given context or time.
-
C.
navalFleet
Indicates a relationship where multiple naval vessels are organized and operate together as a coordinated maritime military force.
-
D.
navalForceComposition
Indicates the makeup and distribution of different types of naval units or vessels within a particular naval force.
-
E.
fleetStrengthEnglish
chosen
Indicates the relative military or naval power level associated with a fleet, expressed or categorized in English terms.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7986d49e0819096c9e96b2ea1b38b |
completed | April 9, 2026, 12:15 p.m. |
| PD | Predicate disambiguation | batch_69d7440da46c8190a77380d5d747ac9c |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.