Triple
T23049001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Premuda |
E573955
|
entity |
| Predicate | nearWreck |
P115718
|
FINISHED |
| Object | SMS Szent István |
—
|
NE NERFINISHED |
How this triple was built (3 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: SMS Szent István | Statement: [Premuda, nearWreck, SMS Szent István]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SMS Szent István Context triple: [Premuda, nearWreck, SMS Szent István]
-
A.
SMS Szent István
chosen
SMS Szent István was a Tegetthoff-class dreadnought battleship of the Austro-Hungarian Navy, best known for being sunk by Italian torpedo boats in 1918 during World War I.
-
B.
Szenttamás
Szenttamás is the Hungarian name for the town of Srbobran in northern Serbia, located in the autonomous province of Vojvodina.
-
C.
Sebestyén
Sebestyén is a Hungarian surname most notably borne by architect Artúr Sebestyén.
-
D.
Pázmány
Pázmány is a Hungarian surname most notably associated with the influential 17th-century Jesuit cardinal and statesman Péter Pázmány.
-
E.
Szent Jobb
Szent Jobb is the revered, mummified right hand relic of Hungary’s first king, Saint Stephen, and a major national and religious symbol preserved in Budapest.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearWreck Context triple: [Premuda, nearWreck, SMS Szent István]
-
A.
containsWreck
Indicates that one entity includes or holds within it the remains or wreckage of another entity.
-
B.
wreckStatus
Indicates the condition or state of damage of an object, typically describing whether and how badly it has been wrecked.
-
C.
wreckLocated
chosen
Indicates that the location of a wreck (such as a destroyed vehicle, ship, or structure) is specified or associated with a particular place or area.
-
D.
wreckDepth
Indicates the depth at which a wreck is located below the water surface.
-
E.
wreckDiscoveryAgent
Indicates that an agent discovers or identifies the wreck of something, such as a destroyed vehicle, vessel, or structure.
- 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_69e245b9c11481909d06c872214d21af |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1867b800881909fabf9dca994c9e7 |
completed | April 29, 2026, 4:18 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:54 p.m.