Triple
T21938233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bugis script |
E541748
|
entity |
| Predicate | hasAlternateName |
P39
|
FINISHED |
| Object | Lontaraq |
—
|
NE NERFINISHED |
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: Lontaraq | Statement: [Bugis script, hasAlternateName, Lontaraq]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lontaraq Context triple: [Bugis script, hasAlternateName, Lontaraq]
-
A.
Lontara
chosen
Lontara is a traditional Brahmic-derived script used primarily for writing the Buginese and several other languages of South Sulawesi, Indonesia.
-
B.
Lontis
Lontis is a settlement located on Buka Island in the Autonomous Region of Bougainville, Papua New Guinea.
-
C.
Lakalai
Lakalai is an Oceanic language spoken by an indigenous community in Papua New Guinea.
-
D.
Labungkari
Labungkari is a town in Indonesia’s Southeast Sulawesi province, known as an administrative and local economic center in the region.
-
E.
Lalolara
Lalolara are a subgroup of the Tolaki people, an indigenous ethnic community of Southeast Sulawesi, Indonesia, with their own distinct cultural and social traditions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1241e35bc81909eb3225d5cd97b92 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:55 p.m.