Triple

T14876063
Position Surface form Disambiguated ID Type / Status
Subject Khairatabad E349869 entity
Predicate near P350 FINISHED
Object Banjara Hills E1123309 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: Banjara Hills | Statement: [Khairatabad, near, Banjara Hills]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banjara Hills
Context triple: [Khairatabad, near, Banjara Hills]
  • A. Banjara Hills chosen
    Banjara Hills is an upscale commercial and residential neighborhood in Hyderabad, India, known for its luxury hotels, shopping areas, and affluent residences.
  • B. Kalyani Nagar
    Kalyani Nagar is an upscale residential and commercial neighborhood in Pune, India, known for its IT parks, shopping malls, and vibrant dining and nightlife options.
  • C. Mukherjee Nagar
    Mukherjee Nagar is a prominent residential and commercial neighborhood in Delhi, India, best known as a major hub for civil services exam coaching centers and student accommodation.
  • D. Indira Nagar
    Indira Nagar is a legislative assembly constituency in the Union Territory of Puducherry, India.
  • E. Indira Nagar
    Indira Nagar is a residential and commercial neighborhood in Chennai, India, known for its urban amenities and proximity to the Adyar area.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5e3e5d48190a132f2cf012b01e2 completed April 15, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72aad76c8190b024651483d8f9ff completed May 8, 2026, 11:32 p.m.
Created at: April 10, 2026, 1:55 a.m.