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.