Triple
T10577035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahavira |
E249636
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Priyadarshana |
E249636
|
NE FINISHED |
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: Priyadarshana | Statement: [Mahavira, child, Priyadarshana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Priyadarshana Context triple: [Mahavira, child, Priyadarshana]
-
A.
Priyadarshana
chosen
Priyadarshana is traditionally regarded as one of the children of Mahavira, the 24th Tirthankara in Jainism.
-
B.
Dasharathi
Dasharathi is an epithet of the Hindu deity Rama, highlighting him as the son of King Dasharatha.
-
C.
Yajnaseni
Yajnaseni is another name for Draupadi, the central heroine of the Indian epic Mahabharata, renowned for her strength, devotion, and pivotal role in the Kurukshetra war.
-
D.
Paramasaugata
Paramasaugata was an honorific royal epithet used for the Pala emperor Devapala, highlighting his status as a supreme devotee and patron of Buddhism.
-
E.
Prasouda
Prasouda is a small Greek island located in the Pagasetic Gulf, known for its tranquil natural setting and proximity to the coast of Thessaly.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5275628988190bd00dd3f8d7c3937 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94b65313481909328bd9f7f39bf53 |
completed | April 10, 2026, 7:11 p.m. |
Created at: April 6, 2026, 12:38 p.m.