Triple

T20130016
Position Surface form Disambiguated ID Type / Status
Subject Bhopal–Indore road E490863 entity
Predicate passesThrough P225 FINISHED
Object Ashta 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: Ashta | Statement: [Bhopal–Indore road, passesThrough, Ashta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ashta
Context triple: [Bhopal–Indore road, passesThrough, Ashta]
  • A. Ashta chosen
    Ashta is a legislative assembly constituency in the Sehore district of the central Indian state of Madhya Pradesh.
  • B. Ashtarak
    Ashtarak is a historic town in western Armenia known for its medieval churches, traditional architecture, and role as a regional cultural center.
  • C. Ashtimki
    Ashtimki is a traditional Tharu festival marked by ritual drawings, storytelling, and communal worship to celebrate the birth of Lord Krishna.
  • D. Astaranga
    Astaranga is a coastal village and emerging tourist spot in Odisha, India, known for its scenic beaches and fishing community.
  • E. Ashtola
    Ashtola is a small unincorporated rural community located in Donley County in the Texas Panhandle.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66760b8f08190a66fbb2e9e3925a3 completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:31 p.m.