Triple
T377359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kannada |
E8600
|
entity |
| Predicate | hasScriptVariant |
P5922
|
FINISHED |
| Object | Tigalari script (historically related) |
—
|
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: Tigalari script (historically related) | Statement: [Kannada, hasScriptVariant, Tigalari script (historically related)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasScriptVariant Context triple: [Kannada, hasScriptVariant, Tigalari script (historically related)]
-
A.
hasVariant
Indicates that one entity exists as an alternative form, version, or variation of another entity.
-
B.
containsScript
Indicates that one entity includes or embeds the script of another entity within it.
-
C.
scriptVariantLanguage
chosen
Indicates that a language is a variant distinguished by its writing system or script from another, related language form.
-
D.
hasVariantSpelling
Indicates that one term is an alternative spelling form of another term.
-
E.
hasUnicodeScript
Indicates that a character or text element belongs to a specific Unicode script category (such as Latin, Cyrillic, or Han).
- 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_69a2e7f47dd08190a4e294ccbbe46cd4 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec1804108190a1e94526b71289ea |
completed | Feb. 28, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69a2e96351cc8190a55adf95f8c27e9e |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.