Triple
T21999027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayurbhanj district |
E543276
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Karanjia |
—
|
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: Karanjia | Statement: [Mayurbhanj district, containsTown, Karanjia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karanjia Context triple: [Mayurbhanj district, containsTown, Karanjia]
-
A.
Karanjia
chosen
Karanjia is a prominent town in the Mayurbhanj district of Odisha, India, known as a local commercial and administrative center for surrounding rural areas.
-
B.
Manjapra
Manjapra is a village in the Ernakulam district of Kerala, India, known for its agrarian landscape and traditional Kerala culture.
-
C.
Kherwara
Kherwara is a town in the Udaipur district of Rajasthan, India, known for its tribal population and location along key regional road routes.
-
D.
Ghansali
Ghansali is a small town in the Indian state of Uttarakhand, situated in the Himalayan region and serving as a local hub for nearby rural areas.
-
E.
Dhundhari
Dhundhari is an Indo-Aryan language spoken primarily in and around Jaipur and adjoining regions of Rajasthan, India.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12768c0088190b0c8d5cd9b7bf710 |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:19 p.m.