Triple
T16964168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tulu script |
E411501
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Tigalari-Malayalam script |
E411501
|
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: Tigalari-Malayalam script | Statement: [Tulu script, alsoKnownAs, Tigalari-Malayalam script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tigalari-Malayalam script Context triple: [Tulu script, alsoKnownAs, Tigalari-Malayalam script]
-
A.
Malayalam script
The Malayalam script is a Brahmic-derived abugida used primarily in the Indian state of Kerala to write the Malayalam language, notable for its rounded letters and extensive set of consonant and vowel signs.
-
B.
Tamil script
Tamil script is an abugida writing system primarily used to write the Tamil language and several other Dravidian and South Asian languages.
-
C.
Bhattiprolu script
The Bhattiprolu script is an ancient Brahmi-derived writing system from the Andhra region of India, considered an early precursor to the Telugu-Kannada scripts.
-
D.
Nandinagari script
Nandinagari script is a historical Brahmic script of southern India, primarily used to write Sanskrit and related languages in the Deccan region.
-
E.
Tulu script
chosen
Tulu script is a historical Brahmic script from southern India traditionally used to write the Tulu language, closely related to the Malayalam script.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d0a2cda88190bd574a869f0e43e9 |
completed | April 18, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b3f751c81908906ec969bef55c5 |
completed | May 10, 2026, 11:56 p.m. |
Created at: April 10, 2026, 5:31 a.m.