Triple
T19707695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parijata tree |
E473257
|
entity |
| Predicate | takenTo |
P2694
|
FINISHED |
| Object | Dvaraka |
—
|
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: Dvaraka | Statement: [Parijata tree, takenTo, Dvaraka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dvaraka Context triple: [Parijata tree, takenTo, Dvaraka]
-
A.
Dvaraka
chosen
Dvaraka is an ancient and sacred coastal city in western India, revered in Hindu tradition as the legendary kingdom of Lord Krishna.
-
B.
Uppala
Uppala is a prominent coastal town in Kerala’s Kasaragod district, known for its commercial activity and proximity to the Kerala–Karnataka border.
-
C.
Kapadapuram
Kapadapuram is a legendary ancient city in Tamil tradition, traditionally regarded as the seat of the Second Sangam, an early Tamil literary academy.
-
D.
Bet Dwarka
Bet Dwarka is a small island off the coast of Gujarat, India, revered in Hindu tradition as a legendary residence of Lord Krishna and an important pilgrimage site.
-
E.
Shringeri
Shringeri is a historic temple town and prominent center of Advaita Vedanta scholarship in Karnataka, India, renowned for its ancient matha and rich manuscript tradition.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642bb5cd4819090e4c62bd74c4324 |
completed | April 20, 2026, 3:14 p.m. |
Created at: April 10, 2026, 1:46 p.m.