Triple
T20964952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Śeṣanāga |
E516342
|
entity |
| Predicate | otherName |
P39
|
FINISHED |
| Object | Śeṣa |
—
|
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: Śeṣa | Statement: [Śeṣanāga, otherName, Śeṣa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Śeṣa Context triple: [Śeṣanāga, otherName, Śeṣa]
-
A.
Śeṣa
chosen
Śeṣa is the cosmic serpent and king of all nāgas in Hindu mythology, often depicted as the multi-headed serpent on whom the god Vishnu reclines.
-
B.
Sudarshana
Sudarshana is a character in the Indian epic Mahabharata, known as the wife of King Virata of Matsya.
-
C.
Mayasura
Mayasura is a legendary architect and king of the Asuras in Hindu mythology, renowned for his extraordinary skill in building magnificent palaces and cities.
-
D.
Kameswara
Kameswara was a king of the Kediri (Kadiri) kingdom in East Java, Indonesia, known from Javanese historical traditions as one of the early rulers in the succession that included the famed King Jayabaya.
-
E.
Surapadman
Surapadman is a powerful demon king in Hindu mythology, best known as the primary adversary defeated by the god Murugan (Skanda) during the events commemorated in the Skanda Sashti festival.
- 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_69e0b4fde6c48190af1398e7e734629e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fb72ef4c8190bebdd2cef3c2148c |
completed | April 21, 2026, 4:22 a.m. |
Created at: April 16, 2026, 1:32 p.m.