Triple
T12348508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oldřich |
E294420
|
entity |
| Predicate | relatedName |
P3889
|
FINISHED |
| Object | Oldrich |
E294420
|
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: Oldrich | Statement: [Oldřich, relatedName, Oldrich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oldrich Context triple: [Oldřich, relatedName, Oldrich]
-
A.
Oldřich
chosen
Oldřich is a Czech masculine given name traditionally borne by several notable historical and cultural figures in the Czech lands.
-
B.
Ondrík
Ondrík is a Slovak diminutive form of the male given name Ondrej, used as an affectionate or familiar variant.
-
C.
Bohuslav
Bohuslav is a Czech masculine given name of Slavic origin, historically borne by several notable figures including composers and politicians.
-
D.
Jodocus
Jodocus is a masculine given name of Latin origin historically borne by figures such as the Flemish cartographer Jodocus Hondius.
-
E.
František
František is a masculine given name of Czech and Slovak origin, equivalent to Francis in English.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7ba17481908b03af7316b28d9b |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6346dd09481908f4c80e89e2f4705 |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:53 p.m.