Triple

T14479809
Position Surface form Disambiguated ID Type / Status
Subject Deccan architecture E359069 entity
Predicate center P4751 FINISHED
Object Golkonda E375898 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: Golkonda | Statement: [Deccan architecture, center, Golkonda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Golkonda
Context triple: [Deccan architecture, center, Golkonda]
  • A. Golkonda chosen
    Golkonda is a historic fortress and former capital of the Qutb Shahi dynasty near Hyderabad in present-day Telangana, India, renowned for its strategic architecture and diamond trade.
  • B. Warangal
    Warangal is a historic city in southern India known for its Kakatiya-era forts, temples, and monuments, and is one of the major urban centers of the state of Telangana.
  • C. Guntakal
    Guntakal is a major railway junction town in Andhra Pradesh, India, serving as an important transit hub on several key rail routes in southern India.
  • D. Bijapur
    Bijapur is a historic city in the Indian state of Karnataka, renowned for its rich Islamic architecture and monuments from the medieval Deccan period.
  • E. Kukatpally
    Kukatpally is a major residential and commercial suburb in Hyderabad, India, known for its dense population, shopping areas, and proximity to the IT corridor.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de924a576c819098351efabdb779b1 completed April 14, 2026, 7:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd64a257488190818c65c1cc84c4b5 completed May 8, 2026, 4:20 a.m.
Created at: April 10, 2026, 1:20 a.m.