Triple
T9021067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manikya dynasty |
E215723
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Udaipur, Tripura |
E287712
|
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: Udaipur, Tripura | Statement: [Manikya dynasty, capital, Udaipur, Tripura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Udaipur, Tripura Context triple: [Manikya dynasty, capital, Udaipur, Tripura]
-
A.
Udaipur
Udaipur is a town in the Lahaul and Spiti district of Himachal Pradesh, India, known for its scenic Himalayan setting and the ancient Mrikula Devi Temple.
-
B.
Udaipur
chosen
Udaipur is a historic town in the Indian state of Tripura, known for its ancient temples and scenic lakes.
-
C.
Udaipur
Udaipur is a historic city in India renowned for its lakes, palaces, and role as a former capital of the Mewar kingdom.
-
D.
Neemuch
Neemuch is a town in northwestern Madhya Pradesh, India, known as an important agricultural and trading center and for hosting a significant military cantonment.
-
E.
Surendranagar
Surendranagar is a city in the Indian state of Gujarat known historically as a regional trade and administrative center.
- 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_69ca83a38aa88190bf1bb80c4548b5e2 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a43add08190983b7ac88576fd7e |
completed | April 1, 2026, 12:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdbb92ffc81909de907f2bb64dd58 |
completed | April 3, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:07 p.m.