Triple
T17981819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuru |
E449618
|
entity |
| Predicate | alliedWith |
P37
|
FINISHED |
| Object | Madra (in epic tradition) |
—
|
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: Madra (in epic tradition) | Statement: [Kuru, alliedWith, Madra (in epic tradition)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madra (in epic tradition) Context triple: [Kuru, alliedWith, Madra (in epic tradition)]
-
A.
Madra
chosen
Madra was an ancient kingdom in the northwest of the Indian subcontinent, frequently mentioned in the Mahabharata and associated with figures like King Shalya and the Pandava prince Nakula.
-
B.
Maduraikāñci
Maduraikāñci is a classical Tamil poem from the Sangam era, renowned for its vivid portrayal of the city of Madurai, its society, and cultural life.
-
C.
Madana
Madana is an Indian film in which actress Zarina Wahab delivered one of her notable performances.
-
D.
goddess Manimekala
Goddess Manimekala is a guardian sea and coastal deity in Tamil tradition, best known for protecting the heroine in the classical epic "Manimekalai."
-
E.
Indra-patni
Indra-patni is a name for the Hindu goddess Shachi, revered as the consort of the god Indra and queen of the heavens.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b20431588190a5fe2148a61de403 |
completed | April 19, 2026, 10:44 a.m. |
Created at: April 10, 2026, 10:22 a.m.