Triple
T23293233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boris II of Bulgaria |
E590090
|
entity |
| Predicate | languageOfState |
P17042
|
FINISHED |
| Object | Old Bulgarian |
—
|
LITERAL 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: Old Bulgarian | Statement: [Boris II of Bulgaria, languageOfState, Old Bulgarian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfState Context triple: [Boris II of Bulgaria, languageOfState, Old Bulgarian]
-
A.
officialLanguageOfSendingState
Indicates that a particular language is the designated official language used by the state that is sending a representative, document, or communication.
-
B.
countryOfficialLanguageStatus
Indicates the status or role that a particular language holds as an official language within a given country.
-
C.
nationalLanguageStatus
chosen
Indicates that a language holds official or nationally recognized status within a country or political entity.
-
D.
nationalLanguageSpoken
Indicates that a particular language is officially recognized and commonly used as a national language within a given country or region.
-
E.
standardLanguageOf
Indicates that one entity serves as the officially recognized or commonly used standard language for another entity (such as a country, region, or organization).
- F. None of above.
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_69e25d1af9d88190a0b9b5e8fa608618 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196ccd9b481909ab5d3504640025e |
completed | April 29, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:02 p.m.