Triple

T11538417
Position Surface form Disambiguated ID Type / Status
Subject Great Calcutta Killings E273607 entity
Predicate location P40 FINISHED
Object Calcutta E4838 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: Calcutta | Statement: [Great Calcutta Killings, location, Calcutta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calcutta
Context triple: [Great Calcutta Killings, location, Calcutta]
  • A. Calcutta chosen
    Calcutta, now known as Kolkata, is a major cultural and commercial metropolis in eastern India that served as the capital of British India until the early 20th century.
  • B. Mambai
    Mambai is an Austronesian language spoken primarily in East Timor, where it is one of the country’s major indigenous languages.
  • C. Chinsurah
    Chinsurah is a historic town in the Hooghly district of West Bengal, India, known for its colonial heritage and educational institutions.
  • D. Garden Reach, Calcutta
    Garden Reach, Calcutta is a riverside neighborhood in Kolkata, India, historically notable as the exiled residence of Awadh’s last Nawab, Wajid Ali Shah.
  • E. Chandannagar
    Chandannagar is a former French colonial town in West Bengal, India, known for its historic riverside architecture and cultural blend of French and Bengali influences.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8839cdf688190ae75c0e6fece8e33 completed April 10, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6859b14e08190b8173a4b5dc8c2c5 completed April 20, 2026, 7:59 p.m.
Created at: April 8, 2026, 9:37 p.m.