Triple

T18290849
Position Surface form Disambiguated ID Type / Status
Subject Kundli industrial area E438108 entity
Predicate locatedIn P40 FINISHED
Object Kundli 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: Kundli | Statement: [Kundli industrial area, locatedIn, Kundli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kundli
Context triple: [Kundli industrial area, locatedIn, Kundli]
  • A. Kundli chosen
    Kundli is a rapidly developing township in Haryana, India, known for its emerging residential and industrial hubs near the Delhi border.
  • B. Chandni
    Chandni is a popular 1989 Hindi romantic musical film starring Sridevi, celebrated for its songs, emotional storyline, and her iconic performance.
  • C. Mehra
    Mehra is an Indian surname commonly associated with North Indian communities and notably borne by figures such as filmmaker Rakeysh Omprakash Mehra.
  • D. Khanna
    Khanna is a prominent town in the Indian state of Punjab, known especially as a major grain market and commercial hub in the region.
  • E. Kalyan
    Kalyan is a long-running Hindi religious and spiritual monthly magazine published by the renowned Geeta Press in India.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e500fee5248190928e68ddaa4d90d7 completed April 19, 2026, 4:21 p.m.
Created at: April 10, 2026, 10:35 a.m.