Triple
T17951860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nakshatras |
E448848
|
entity |
| Predicate | systemIncludes |
P1393
|
FINISHED |
| Object | Revati |
—
|
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: Revati | Statement: [Nakshatras, systemIncludes, Revati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Revati Context triple: [Nakshatras, systemIncludes, Revati]
-
A.
Revati
chosen
Revati is a princess from Hindu mythology, known as the daughter of King Kakudmi and the wife of the deity Balarama.
-
B.
Shravika
Shravika is the term in Jainism for a female lay follower who observes religious vows and practices while living a household life.
-
C.
Surabhi
Surabhi is a divine cow-goddess in Hindu mythology, revered as the mother of cattle and a symbol of abundance and nourishment.
-
D.
Visalakshi
Visalakshi is a revered form of the Hindu goddess Parvati worshipped as the divine consort of Lord Shiva at the Kasi Viswanathar Temple in Kumbakonam.
-
E.
Madhavi
Madhavi is a celebrated courtesan and pivotal literary figure in ancient Tamil epic tradition, prominently featured in the Sangam-era works Silappatikaram and its sequel Manimekalai.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afad61f481908b34cd24de88983c |
completed | April 19, 2026, 10:34 a.m. |
Created at: April 10, 2026, 10:21 a.m.