Triple
T20933550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulgarian Sign Language |
E515525
|
entity |
| Predicate | hasLinguisticModality |
P88337
|
FINISHED |
| Object | manual-visual |
—
|
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: manual-visual | Statement: [Bulgarian Sign Language, hasLinguisticModality, manual-visual]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLinguisticModality Context triple: [Bulgarian Sign Language, hasLinguisticModality, manual-visual]
-
A.
languageModality
chosen
Indicates the mode or form in which a language is expressed or perceived (e.g., spoken, signed, written, or tactile).
-
B.
hasLinguisticDomain
Indicates that something (such as a term, expression, or resource) is associated with or applies within a particular linguistic domain or language context.
-
C.
hasLinguisticFeature
Indicates that an entity possesses a particular linguistic property, trait, or characteristic.
-
D.
hasLinguisticDocumentation
Indicates that there exists recorded linguistic information or documentation about the language or linguistic properties of the subject.
-
E.
hasVerbalSystem
Indicates that an entity possesses or is characterized by a particular system of verbal or spoken language forms and structures.
- 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.