Triple
T8559910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhai Dooj |
E202664
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Yama Dwitiya |
E42391
|
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: Yama Dwitiya | Statement: [Bhai Dooj, associatedWith, Yama Dwitiya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yama Dwitiya Context triple: [Bhai Dooj, associatedWith, Yama Dwitiya]
-
A.
Yama
chosen
Yama is the Hindu god of death and justice, traditionally regarded as the ruler of the afterlife and judge of the souls of the dead.
-
B.
Yama
Yama is the historical name of the Russian town now known as Kingisepp, located in Leningrad Oblast near the border with Estonia.
-
C.
Yama
Yama is a Linux Security Module that enhances process and ptrace-related security by restricting how processes can inspect or interfere with each other.
-
D.
Sadyojata
Sadyojata is one of the five faces of Lord Shiva, symbolizing creation and the westward aspect of the deity in Shaivite tradition.
-
E.
Yama Jigoku
Yama Jigoku is one of Beppu’s famous “hell” hot spring sites, known for its boiling, vividly colored pools and dramatic geothermal scenery.
- 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_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe949974c8190a75d9c767ca5fa5a |
completed | March 31, 2026, 3:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebb84a6988190ba6852f72c8918ca |
completed | April 2, 2026, 6:55 p.m. |
Created at: March 30, 2026, 6:20 p.m.