Triple
T19594640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kosala kingdom |
E470319
|
entity |
| Predicate | notableRuler |
P22
|
FINISHED |
| Object | Prasenajit |
—
|
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: Prasenajit | Statement: [Kosala kingdom, notableRuler, Prasenajit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prasenajit Context triple: [Kosala kingdom, notableRuler, Prasenajit]
-
A.
Prasenajit
chosen
Prasenajit was an ancient Indian monarch of the kingdom of Kosala, known from Buddhist and Jain traditions as a contemporary and patron of the Buddha.
-
B.
Bijayananda
Bijayananda is the full given name of Biju Patnaik, a prominent Indian politician and former Chief Minister of Odisha.
-
C.
Barindra
Barindra is an Indian given name most notably associated with Barindra Kumar Ghosh, a revolutionary involved in the Indian independence movement.
-
D.
Shamindranath
Shamindranath is the given name of Shamindranath Tagore, a member of the prominent Tagore family associated with Bengali literature and culture.
-
E.
Sutanu
Sutanu is a character in the Indian epic Mahabharata, known as one of the sons of King Virata of Matsya.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640793cd88190b9b84491bfb2493f |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.