Triple
T21037083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Géza, Grand Prince of the Hungarians |
E518217
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Grand Prince |
—
|
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: Grand Prince | Statement: [Géza, Grand Prince of the Hungarians, title, Grand Prince]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grand Prince Context triple: [Géza, Grand Prince of the Hungarians, title, Grand Prince]
-
A.
Grand Prince
chosen
Grand Prince was the medieval title held by the supreme ruler of the early Hungarian state before it became a Christian kingdom.
-
B.
Fürst
Fürst is a German noble title historically ranking below a duke and above a count, often translated as "prince" in English.
-
C.
Prince of Verden
The Prince of Verden was the secular ruler of the former Prince-Bishopric of Verden in the Holy Roman Empire, holding both territorial and noble authority over the region.
-
D.
Prinze
Prinze is the surname of American actor Freddie Prinze Jr., associated with a family of entertainers in film and television.
-
E.
Prince Toneri
Prince Toneri was an 8th-century Japanese imperial prince and scholar best known for overseeing the compilation of the historical chronicle Nihon Shoki.
- 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_69e0b503275c8190afd9a163f997c709 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fcecf2508190a7647abb3c59debb |
completed | April 21, 2026, 4:28 a.m. |
Created at: April 16, 2026, 2:02 p.m.