Triple
T19428733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trishira |
E486051
|
entity |
| Predicate | siblingOf |
P363
|
FINISHED |
| Object | Narantaka |
—
|
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: Narantaka | Statement: [Trishira, siblingOf, Narantaka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Narantaka Context triple: [Trishira, siblingOf, Narantaka]
-
A.
Narantaka
chosen
Narantaka is a lesser-known demon warrior from the Hindu epic Ramayana, depicted as one of Ravana’s sons who fights in the great battle of Lanka.
-
B.
Hiniraya
Hiniraya is an alternate name for Kinaray-a, an Austronesian language spoken primarily in the Western Visayas region of the Philippines.
-
C.
Ratak
Ratak is a chain of low-lying coral atolls and islands in the Marshall Islands, located in the central Pacific Ocean and known for its remote, sparsely populated communities.
-
D.
Nakoruru
Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
-
E.
Kamsa
Kamsa is a tyrannical king in Hindu mythology, best known as the evil uncle and nemesis of Lord Krishna.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6321b78d08190b86cef7c60cbb61c |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.