Triple
T15105665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franz von Stuck |
E360781
|
entity |
| Predicate | nobleTitle |
P914
|
FINISHED |
| Object | Ritter von Stuck |
E887556
|
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: Ritter von Stuck | Statement: [Franz von Stuck, nobleTitle, Ritter von Stuck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ritter von Stuck Context triple: [Franz von Stuck, nobleTitle, Ritter von Stuck]
-
A.
Ritter
Ritter is the surname of Thelma Ritter, the acclaimed American character actress known for her sharp-tongued, working-class roles in mid-20th-century Hollywood films.
-
B.
Ritter
chosen
Ritter is a historical German noble title roughly equivalent to a knight, traditionally ranking below a baron in the aristocratic hierarchy.
-
C.
Ritter
Ritter is a small lunar impact crater located on the western edge of Mare Tranquillitatis on the Moon.
-
D.
Prince of Grubenhagen
The Prince of Grubenhagen was a ruler from a cadet branch of the House of Welf who governed the small principality of Grubenhagen within the Holy Roman Empire.
-
E.
Herzog von Oels
Herzog von Oels was the German ducal title borne by the Piast rulers of the Silesian duchy centered on Oleśnica (Oels) in present-day Poland.
- 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00588f35481909674f161bf0f3918 |
completed | April 15, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feae28e99881908156909e553c2538 |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 3:05 a.m.