Triple
T20637722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sathyandranath Ragunanan |
E507129
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Mac Maharaj |
—
|
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: Mac Maharaj | Statement: [Sathyandranath Ragunanan, alsoKnownAs, Mac Maharaj]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mac Maharaj Context triple: [Sathyandranath Ragunanan, alsoKnownAs, Mac Maharaj]
-
A.
Mac Maharaj
chosen
Mac Maharaj is a prominent South African anti-apartheid activist and politician of Indian descent who played a key role in the struggle against apartheid and later served in senior government positions.
-
B.
Kishan Maharaj
Kishan Maharaj was a renowned Indian tabla virtuoso celebrated for his mastery of the Banaras gharana and his powerful, intricate rhythmic compositions.
-
C.
Mamik Singh
Mamik Singh is an Indian actor best known for his role in the cult classic sports drama film "Jo Jeeta Wohi Sikandar."
-
D.
Jagatraj
Jagatraj was a prince of the Bundela dynasty, known as a son of the famed Bundelkhand ruler Maharaja Chhatrasal.
-
E.
Lala Ramjas
Lala Ramjas was an Indian philanthropist and educationist after whom Delhi University’s Ramjas College is named.
- 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_69e0b4be702c8190a3d2410a881d310a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6ad1089448190b936de6fd29c8350 |
completed | April 20, 2026, 10:47 p.m. |
Created at: April 16, 2026, 11:42 a.m.