Triple
T10914698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Central Dravidian |
E257788
|
entity |
| Predicate | hasDescendant |
P3654
|
FINISHED |
| Object | Naiki |
E173500
|
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: Naiki | Statement: [Proto-Central Dravidian, hasDescendant, Naiki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naiki Context triple: [Proto-Central Dravidian, hasDescendant, Naiki]
-
A.
Naiki
chosen
Naiki is a Dravidian language spoken by indigenous communities in central India, particularly in parts of Maharashtra and adjoining regions.
-
B.
Nikiya
Nikiya is the tragic temple dancer heroine of the classical ballet *La Bayadère*, renowned for her ethereal presence and doomed love story.
-
C.
Naicker
Naicker is an Indian-origin surname commonly found in South Asia, particularly among Tamil-speaking communities.
-
D.
Naikū
Naikū is the inner sanctuary of Japan’s Ise Grand Shrine, dedicated to the sun goddess Amaterasu and regarded as one of Shinto’s most sacred sites.
-
E.
Nikare
Nikare was a little-known pharaoh who ruled during Egypt’s Eighth Dynasty in the early First Intermediate Period.
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77073d12881908ea59771b84bc804 |
completed | April 9, 2026, 9:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e216eb77dc81908c380f5fcd507275 |
completed | April 17, 2026, 11:18 a.m. |
Created at: April 8, 2026, 9:22 p.m.