Triple
T17268269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mapanji Jayashakti |
E419185
|
entity |
| Predicate | countryOfCitizenship |
P2
|
FINISHED |
| Object | Kahuripan |
—
|
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: Kahuripan | Statement: [Mapanji Jayashakti, countryOfCitizenship, Kahuripan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kahuripan Context triple: [Mapanji Jayashakti, countryOfCitizenship, Kahuripan]
-
A.
Kahuripan
chosen
Kahuripan was an early 11th-century Javanese kingdom in eastern Java that emerged after the fall of the Medang Kingdom and laid the groundwork for later states like Kediri.
-
B.
Kwararafa
Kwararafa was a historical multi-ethnic confederation and powerful kingdom in what is now central Nigeria, known for its military campaigns and interactions with neighboring Hausa states.
-
C.
Kükita
Kükita is a small settlement located in Järva County in central Estonia.
-
D.
Takabisha
Takabisha is a record-breaking steel roller coaster in Japan renowned for its extremely steep drop and intense thrill elements.
-
E.
Parukotoan
Parukotoan is a small South American indigenous language subgroup that includes languages such as Wayana, spoken primarily in the Guiana region.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42f4683c4819083a210255662136c |
completed | April 19, 2026, 1:26 a.m. |
Created at: April 10, 2026, 5:40 a.m.