Triple
T3924281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Panji Tohjaya |
E93234
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Mahisa Campaka |
E400356
|
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: Mahisa Campaka | Statement: [Panji Tohjaya, relative, Mahisa Campaka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mahisa Campaka Context triple: [Panji Tohjaya, relative, Mahisa Campaka]
-
A.
Mahisa Campaka
chosen
Mahisa Campaka was a ruler in the Singhasari kingdom of Java, known for preceding and being succeeded by Panji Tohjaya in the 13th century.
-
B.
Taur Matan Ruak
Taur Matan Ruak is an East Timorese military leader and politician who served as commander of the national defence force and later as President of Timor-Leste.
-
C.
Maufra
Maufra is a French surname most notably associated with the landscape painter and printmaker Maxime Maufra, linked to the Impressionist and Pont-Aven movements.
-
D.
Mount Loilaeng
Mount Loilaeng is a prominent peak in eastern Myanmar, recognized as the highest mountain in the Shan Hills range.
-
E.
Mahameru
Mahameru is the revered local name for Mount Semeru, the highest and one of the most active volcanoes on the island of Java in Indonesia.
- 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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeed7dacdc8190854ebc13db2d24bc |
completed | March 9, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b53387775881909479f4e1fcecdaca |
completed | March 14, 2026, 10:08 a.m. |
Created at: March 9, 2026, 3:23 p.m.