Triple

T15206145
Position Surface form Disambiguated ID Type / Status
Subject Devi Lal E363393 entity
Predicate placeOfDeath P21 FINISHED
Object New Delhi, India E3459 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: New Delhi, India | Statement: [Devi Lal, placeOfDeath, New Delhi, India]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Delhi, India
Context triple: [Devi Lal, placeOfDeath, New Delhi, India]
  • A. New Delhi, India chosen
    New Delhi, India is the capital city of India, serving as the nation’s political and administrative center and home to key government institutions and historic landmarks.
  • B. Delhi
    Delhi is a major metropolitan region and the capital territory of India, known for its political significance, rich history, and diverse culture.
  • C. Indiranagar
    Indiranagar is a prominent residential and commercial neighborhood in eastern Bengaluru, known for its upscale eateries, pubs, and shopping streets.
  • D. Pusa, New Delhi
    Pusa, New Delhi is a locality in the Indian capital best known as a major agricultural research and education hub.
  • E. West Delhi
    West Delhi is an administrative district in the western part of India’s National Capital Territory of Delhi, known for its dense residential neighborhoods and bustling commercial areas.
  • 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e006b7964c8190bc8dc3444b94f15e completed April 15, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff2190cd748190b87279605280c54c completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:11 a.m.