Triple
T9020143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashti taluka |
E215700
|
entity |
| Predicate | administrativeCentre |
P1474
|
FINISHED |
| Object | Ashti |
E212431
|
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: Ashti | Statement: [Ashti taluka, administrativeCentre, Ashti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ashti Context triple: [Ashti taluka, administrativeCentre, Ashti]
-
A.
Ashti
chosen
Ashti is a town in the Wardha district of Maharashtra, India, known primarily as a local administrative and agricultural center.
-
B.
Atessa
Atessa is a town and municipality in the Abruzzo region of central Italy, known for its industrial activity and automotive manufacturing facilities.
-
C.
Asti
Asti is a historic city in Italy’s Piedmont region, renowned for its sparkling wines, medieval architecture, and cultural traditions.
-
D.
Ypati
Ypati is a historic town in central Greece, known for its mountainous setting near Mount Oeta and its role in various periods of Greek history.
-
E.
Akrosh
Akrosh is an Indian film best known as a hard-hitting social drama written by acclaimed playwright and screenwriter Vijay Tendulkar.
- 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_69cc6a421c2c8190abb12c826066fe75 |
completed | April 1, 2026, 12:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdbaf7be081908738ef9a9a17a77b |
completed | April 3, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:07 p.m.