Triple
T7518745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sawu language |
E177711
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Hawun |
E670426
|
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: Hawun | Statement: [Sawu language, hasAlternativeName, Hawun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hawun Context triple: [Sawu language, hasAlternativeName, Hawun]
-
A.
Hawu
chosen
Hawu is an Austronesian language spoken primarily on Savu (Sawu) Island in East Nusa Tenggara, Indonesia.
-
B.
Hwaci
Hwaci is the small American software company best known for creating and maintaining the SQLite relational database engine.
-
C.
Harku
Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
-
D.
Hybe
Hybe is a historic village in northern Slovakia’s Liptov region, known for its traditional architecture and scenic mountainous surroundings.
-
E.
Huwon
Huwon is the secret rear garden of Changdeokgung Palace in Seoul, renowned for its landscaped ponds, pavilions, and natural woodland used historically as a royal retreat.
- 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_69c69f2891148190a484f3b8222c6f1b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5f850c081909e697219071293fc |
completed | March 27, 2026, 9:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84ef834608190bf425f99222a4bc5 |
completed | March 28, 2026, 9:58 p.m. |
Created at: March 27, 2026, 3:46 p.m.