Triple

T9768254
Position Surface form Disambiguated ID Type / Status
Subject Shibpur E237052 entity
Predicate near P350 FINISHED
Object Howrah Maidan E727494 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: Howrah Maidan | Statement: [Shibpur, near, Howrah Maidan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howrah Maidan
Context triple: [Shibpur, near, Howrah Maidan]
  • A. Howrah Maidan chosen
    Howrah Maidan is a prominent commercial and transit hub in Howrah, West Bengal, known for its busy markets and connectivity to Kolkata and surrounding areas.
  • B. Pragati Maidan
    Pragati Maidan is a major exhibition and convention center in New Delhi, India, known for hosting large trade fairs, expos, and cultural events.
  • C. Nehru Maidan
    Nehru Maidan is a sports ground in Rajkot, India, primarily used for local cricket and other sporting events.
  • D. Khule Maidan
    Khule Maidan is a notable work by Indian writer Puran Singh, recognized for its literary and cultural significance in Punjabi/Hindi literature.
  • E. Vivekananda Yuba Bharati Krirangan
    Vivekananda Yuba Bharati Krirangan is a large multi-purpose stadium in Kolkata, India, best known as one of the country’s premier football venues and formerly one of the largest stadiums in the world by seating capacity.
  • 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_69ca84d831b8819090322686b47887ce completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda0a2da648190836916a45d2998d7 completed April 1, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bd05f2588190ab413d26342aa70f completed April 5, 2026, 1:38 a.m.
Created at: March 30, 2026, 8:25 p.m.