Triple
T9052016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unicode 3.0 |
E216905
|
entity |
| Predicate | addsScripts |
P47137
|
FINISHED |
| Object | Thaana |
E43230
|
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: Thaana | Statement: [Unicode 3.0, addsScripts, Thaana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thaana Context triple: [Unicode 3.0, addsScripts, Thaana]
-
A.
Thaana script
chosen
Thaana script is a unique writing system used primarily for the Maldivian (Dhivehi) language, written from right to left and combining features of both Indic and Arabic scripts.
-
B.
Ganjami
Ganjami is a regional dialect of the Odia language spoken primarily in the Ganjam region of Odisha, India.
-
C.
Mata Gujri
Mata Gujri was a revered Sikh matriarch and historical figure, best known as the mother of Guru Gobind Singh and grandmother of the four Sahibzadas who were martyred for the Sikh faith.
-
D.
Qrami
Qrami is the Azerbaijani name for the Khrami River, a tributary of the Kura River flowing through Georgia and Azerbaijan.
-
E.
Kurukh
Kurukh is an indigenous Dravidian language spoken primarily by the Oraon tribal communities in eastern and central India.
- 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_69ca83d362e88190ae44b4e4dc194209 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc7a700de48190aa9f61d850e01cbd |
completed | April 1, 2026, 1:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfebd1450c819092dccae2c48b100d |
completed | April 3, 2026, 4:33 p.m. |
Created at: March 30, 2026, 7:10 p.m.