Triple
T22931200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Nissanka Malla |
E569442
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Maha Raja |
—
|
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: Maha Raja | Statement: [King Nissanka Malla, title, Maha Raja]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maha Raja Context triple: [King Nissanka Malla, title, Maha Raja]
-
A.
Raja Maharaj
Raja Maharaj is the revered monastic name of Swami Brahmananda, a direct disciple of Sri Ramakrishna and the first president of the Ramakrishna Math and Mission.
-
B.
Maharajadhiraja
Maharajadhiraja is an ancient Indian royal title signifying a "great king of kings," denoting a sovereign of the highest imperial rank.
-
C.
Raja
chosen
Raja is a traditional Indian royal title historically used by Hindu monarchs and regional rulers.
-
D.
Sangrama Raja
Sangrama Raja was an early medieval ruler of Kashmir who established the Lohara dynasty, which became a significant royal house in the region.
-
E.
Rajarshi
Rajarshi is an honorific title in ancient Indian tradition denoting a king who has attained the spiritual wisdom and detachment of a sage.
- 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_69e2458f7d008190901dccbaebeaba24 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18131956c8190b8c850fc1d57a119 |
completed | April 29, 2026, 3:55 a.m. |
Created at: April 17, 2026, 3:44 p.m.