Triple
T20933551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulgarian Sign Language |
E515525
|
entity |
| Predicate | hasDistinctLexiconFrom |
P12379
|
FINISHED |
| Object | spoken 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: spoken Bulgarian | Statement: [Bulgarian Sign Language, hasDistinctLexiconFrom, spoken Bulgarian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistinctLexiconFrom Context triple: [Bulgarian Sign Language, hasDistinctLexiconFrom, spoken Bulgarian]
-
A.
hasDistinctVocabulary
chosen
Indicates that one entity’s vocabulary is different or distinguishable from that of another entity.
-
B.
hasDistinctOrthographyFrom
Indicates that two written forms are orthographically different from each other, even if they may represent the same or related linguistic content.
-
C.
hasLexiconPreservedIn
Indicates that the lexicon of one entity is preserved, recorded, or stored within another entity.
-
D.
hasLexicalDifferencesWith
Indicates that two linguistic items differ from each other in their word choice or lexical form.
-
E.
hasDistinctPronounsFrom
Indicates that two entities use different sets of pronouns from each other.
- 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_69e0b4fc13408190b06868df03c5c29b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f94e980c819083280a9c35af5930 |
completed | April 21, 2026, 4:13 a.m. |
| PD | Predicate disambiguation | batch_69e5c9af1fe08190953366a466950140 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:49 p.m.