Triple
T22092105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devanampriya Priyadarshi |
E545936
|
entity |
| Predicate | script |
P505
|
FINISHED |
| Object | Brahmi |
—
|
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: Brahmi | Statement: [Devanampriya Priyadarshi, script, Brahmi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brahmi Context triple: [Devanampriya Priyadarshi, script, Brahmi]
-
A.
Brahmi
chosen
Brahmi is an ancient Indian writing system, considered one of the earliest scripts of the Indian subcontinent and the ancestor of many modern South and Southeast Asian scripts.
-
B.
Matsyagandha
Matsyagandha is an epithet of Satyavati, the fisherwoman-turned-queen in the Indian epic Mahabharata, known as the mother of sage Vyasa and ancestress of the Kuru dynasty.
-
C.
Bacopa monnieri
Bacopa monnieri is a creeping, water-loving herb widely used in traditional Ayurvedic medicine as a nootropic for enhancing memory and cognitive function.
-
D.
Nishadha
Nishadha is an ancient Indian kingdom mentioned in classical Sanskrit literature, particularly the Mahabharata and related epics.
-
E.
Sanjeevani herb
The Sanjeevani herb is a legendary life-restoring plant in Hindu mythology, famed for its power to revive the mortally wounded.
- 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_69e11e36d03c8190a83a1ba802b7231b |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128e5edf08190a6743955bc872417 |
completed | April 28, 2026, 9:38 p.m. |
Created at: April 16, 2026, 8:29 p.m.