Triple
T16815531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johann Kaspar Wilcke |
E408735
|
entity |
| Predicate | hasGivenName |
P17
|
FINISHED |
| Object | Kaspar |
E1039984
|
NE 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: Kaspar | Statement: [Johann Kaspar Wilcke, hasGivenName, Kaspar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaspar Context triple: [Johann Kaspar Wilcke, hasGivenName, Kaspar]
-
A.
Kaspar
chosen
Kaspar is a 1967 play by Austrian writer Peter Handke that explores language, identity, and social conditioning through the story of a speechless outsider molded by external voices.
-
B.
Kasper
Kasper is a surname most notably associated with former American football wide receiver Kevin Kasper.
-
C.
Caspar
Caspar is one of the Three Wise Men in Christian tradition, often depicted as a king who visited the infant Jesus bearing gifts.
-
D.
Bertholdt
Bertholdt is a variant spelling of the German given name Berthold, historically borne by various notable figures in German-speaking regions.
-
E.
Karl
Karl is a ruthless, long-haired German terrorist and Hans Gruber’s vengeful right-hand man in the action film "Die Hard."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b2e0e05081908bd5eaa64abe133d |
completed | April 18, 2026, 4:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b2946ddc81908b1e7c662dc943ff |
completed | May 10, 2026, 4:30 p.m. |
Created at: April 10, 2026, 5:23 a.m.