Triple
T7917560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahipala I |
E183864
|
entity |
| Predicate | placeOfRule |
P46958
|
FINISHED |
| Object | Varendra |
E671163
|
NE FINISHED |
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: Varendra | Statement: [Mahipala I, placeOfRule, Varendra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Varendra Context triple: [Mahipala I, placeOfRule, Varendra]
-
A.
Varendra
chosen
Varendra is a historic region in northwestern Bengal, now largely in Bangladesh, known as an early political and cultural center of medieval Bengali kingdoms.
-
B.
Gobardanga
Gobardanga is a town in the Indian state of West Bengal known for its suburban character and connectivity to Kolkata via the Sealdah–Bangaon railway line.
-
C.
Pandua
Pandua is a historic city in present-day West Bengal, India, that served as an important political and cultural center during the medieval Bengal Sultanate.
-
D.
Baria
Baria is an alternative name for the city of Nara, an ancient cultural and historical center in Japan renowned for its temples and traditional heritage.
-
E.
Bhatarka
Bhatarka was an early Indian ruler who founded the Maitraka dynasty, establishing its power base in the region of present-day Gujarat.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a8e8b388190b5544eb5b8159e07 |
completed | March 31, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc563cb0a081909ed43ff45a8a1fa0 |
completed | March 31, 2026, 11:18 p.m. |
Created at: March 30, 2026, 5:05 p.m.