Triple
T22937392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madhav Vilas Palace |
E569622
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Shivpuri |
—
|
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: Shivpuri | Statement: [Madhav Vilas Palace, city, Shivpuri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shivpuri Context triple: [Madhav Vilas Palace, city, Shivpuri]
-
A.
Shivpuri
chosen
Shivpuri is a historic town and former princely state in central India, known for its forests, wildlife sanctuaries, and royal palaces.
-
B.
Sonpur
Sonpur is a town in the Indian state of Bihar, known for its location near the confluence of the Ganges and Gandak rivers and for hosting one of Asia’s largest traditional cattle fairs.
-
C.
Chandanpura
Chandanpura is a locality in Chittagong, Bangladesh, known for its historic architecture and urban commercial activity.
-
D.
Sohagpur
Sohagpur is a town in the Narmadapuram district of Madhya Pradesh, India, known as a local commercial center and access point to nearby forested and wildlife areas.
-
E.
Sitapur
Sitapur is a prominent city and administrative center in the Indian state of Uttar Pradesh, known for its agricultural trade and regional connectivity.
- 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_69e24590862c8190858f180ad302adab |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18136bf448190afa04f8b55a8bb6e |
completed | April 29, 2026, 3:55 a.m. |
Created at: April 17, 2026, 3:45 p.m.