Triple
T17937579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andhaka |
E448507
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Ugrasena |
—
|
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: Ugrasena | Statement: [Andhaka, hasMember, Ugrasena]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ugrasena Context triple: [Andhaka, hasMember, Ugrasena]
-
A.
Ugrasena
chosen
Ugrasena is a legendary king in Hindu mythology, known as a ruler of the Yadava clan and the grandfather of Krishna.
-
B.
Yudhajit
Yudhajit is a lesser-known prince in the Ramayana, recognized as the brother of Queen Kaikeyi and thus an uncle of Bharata.
-
C.
Surasena
Surasena was an ancient Indian kingdom and one of the sixteen Mahajanapadas, centered around its capital Mathura in the northern Indian subcontinent.
-
D.
Jayadratha
Jayadratha is a king from the Indian epic Mahabharata, best known for his role in the death of Abhimanyu and his subsequent slaying by Arjuna.
-
E.
Indrajit
Indrajit is a powerful warrior prince in the Hindu epic Ramayana, famed for his mastery of celestial weapons and for being the formidable son of the demon king Ravana.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad937f0881909d22ac8c2be9e35e |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 10:21 a.m.