Triple
T21042897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wajo |
E518372
|
entity |
| Predicate | rulingOffice |
P21569
|
FINISHED |
| Object | Arung Matoa |
—
|
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: Arung Matoa | Statement: [Wajo, rulingOffice, Arung Matoa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arung Matoa Context triple: [Wajo, rulingOffice, Arung Matoa]
-
A.
Arung Matoa
chosen
Arung Matoa was the highest political leader of the Kingdom of Wajo in South Sulawesi, traditionally chosen through a collective decision-making process among local nobles.
-
B.
Ranu Pakis
Ranu Pakis is a volcanic crater lake in East Java, Indonesia, known for its scenic setting near Mount Lamongan.
-
C.
Rambu Tuka'
Rambu Tuka' is a traditional Torajan thanksgiving ceremony that celebrates life, prosperity, and the rice harvest with communal rituals, offerings, and festivities.
-
D.
Arung Mangkau
Arung Mangkau is the royal title used for the monarch of the Kingdom of Bone, a historical Bugis state in South Sulawesi, Indonesia.
-
E.
Orang Pendek
Orang Pendek is a cryptid from Sumatran folklore, typically described as a small, bipedal, ape-like creature said to inhabit the island’s remote rainforests.
- 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_69e0b50438e08190917e2538bb8bc034 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fcf1950081908ff9fe8719e1e81b |
completed | April 21, 2026, 4:28 a.m. |
Created at: April 16, 2026, 2:17 p.m.