Triple
T19429279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keshi |
E486066
|
entity |
| Predicate | sentBy |
P4409
|
FINISHED |
| Object | Kamsa |
—
|
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: Kamsa | Statement: [Keshi, sentBy, Kamsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kamsa Context triple: [Keshi, sentBy, Kamsa]
-
A.
Kamsa
chosen
Kamsa is a tyrannical king in Hindu mythology, best known as the evil uncle and nemesis of Lord Krishna.
-
B.
Koshun
Koshun is a music producer known for working on projects associated with the artist Amala.
-
C.
Kanuma
Kanuma is a city in Japan’s Tochigi Prefecture known for its traditional wooden floats, historic streets, and the annual Kanuma Autumn Festival.
-
D.
Kanuma
Kanuma is a regional harvest festival celebrated mainly in Andhra Pradesh and Telangana as part of the multi-day Makar Sankranti festivities, focusing on cattle worship and agricultural prosperity.
-
E.
Bwonsamdi
Bwonsamdi is a powerful loa of death in the Warcraft universe, known for overseeing the spirits of the dead and striking dark bargains with mortals.
- 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.