Triple
T1082498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malay |
E23976
|
entity |
| Predicate | scriptVariant |
P4680
|
FINISHED |
| Object | Jawi |
E118143
|
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: Jawi | Statement: [Malay, scriptVariant, Jawi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jawi Context triple: [Malay, scriptVariant, Jawi]
-
A.
Jawi script
chosen
Jawi script is an Arabic-based writing system historically used for various Malayic languages in Southeast Asia, including Minangkabau, for religious, literary, and administrative purposes.
-
B.
Javanese script
The Javanese script is a traditional Brahmic-derived abugida used historically and culturally for writing the Javanese language, especially on the island of Java in Indonesia.
-
C.
Sundanese script
The Sundanese script is an abugida used historically and in modern times to write the Sundanese language of West Java, Indonesia.
-
D.
Kawi script
Kawi script is an ancient Brahmic-derived writing system historically used across Java and other parts of Southeast Asia to write Old Javanese and related languages.
-
E.
Balinese script
Balinese script is an abugida used primarily on the Indonesian island of Bali for writing the Balinese language, as well as liturgical and historical texts in Sanskrit and Old Javanese.
- 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_69a493f1ddf48190a99d54b00e99f8ce |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b95e56948190a1e92367ad7240b7 |
completed | March 1, 2026, 10:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac763a7cd481909bf83a2e67c0d9f5 |
completed | March 7, 2026, 7:02 p.m. |
Created at: March 1, 2026, 7:42 p.m.