Triple
T22078512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skjold-class corvette |
E545583
|
entity |
| Predicate | namesake |
P63
|
FINISHED |
| Object | Skjold |
—
|
NE NERFINISHED |
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: Skjold | Statement: [Skjold-class corvette, namesake, Skjold]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skjold Context triple: [Skjold-class corvette, namesake, Skjold]
-
A.
Skjolden
Skjolden is a small Norwegian village located at the innermost end of a branch of the Sognefjord, surrounded by dramatic fjord and mountain scenery.
-
B.
Skjöld
chosen
Skjöld is a legendary Danish king in Norse mythology, often regarded as the founder of the Skjöldung (Scylding) dynasty.
-
C.
Tordenskjold
Tordenskjold was a famed early 18th-century Norwegian-Danish naval hero and officer known for his daring exploits against Sweden during the Great Northern War.
-
D.
Vikingen
Vikingen is a notable literary work by Swedish writer, historian, and philosopher Erik Gustaf Geijer.
-
E.
Viking Flagship
Viking Flagship was a top-class British National Hunt racehorse best known as a dual Queen Mother Champion Chase winner in the 1990s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3523488190badd54b5d580c00d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128b43df0819090c248ded98fad12 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.