Triple
T21780926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prabu Padjadjaran |
E537708
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Prabu |
—
|
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: Prabu | Statement: [Prabu Padjadjaran, title, Prabu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prabu Context triple: [Prabu Padjadjaran, title, Prabu]
-
A.
Prabu
chosen
Prabu is a royal title historically used for kings or rulers in the Sundanese Kingdom of West Java, Indonesia.
-
B.
Prabu Padjadjaran
Prabu Padjadjaran is a legendary Sundanese king associated with the historical Padjadjaran kingdom in West Java, Indonesia.
-
C.
Samaratungga
Samaratungga was a 9th-century Javanese king of the Sailendra dynasty best known for commissioning the construction of the monumental Borobudur Buddhist temple in Central Java.
-
D.
Tribhuwana
Tribhuwana is the regnal name of a 14th-century Javanese queen of the Majapahit Empire, formally known as Tribhuwana Wijayatunggadewi.
-
E.
Jayabaya
Jayabaya was a legendary 12th-century king of the Kediri Kingdom in Java, renowned in Indonesian history and folklore for his just rule and prophetic visions.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0462cae6481908d3e7f71683d8921 |
completed | April 28, 2026, 5:31 a.m. |
Created at: April 16, 2026, 6:52 p.m.