Triple

T19625308
Position Surface form Disambiguated ID Type / Status
Subject Pulok Chatterji E471117 entity
Predicate workedUnder P3062 FINISHED
Object Manmohan Singh 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: Manmohan Singh | Statement: [Pulok Chatterji, workedUnder, Manmohan Singh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manmohan Singh
Context triple: [Pulok Chatterji, workedUnder, Manmohan Singh]
  • A. Manmohan Singh chosen
    Manmohan Singh is an Indian economist and politician who served as the 13th Prime Minister of India from 2004 to 2014.
  • B. Giani Zail Singh
    Giani Zail Singh was an Indian politician who served as the seventh President of India and was previously the country's Home Minister and Chief Minister of Punjab.
  • C. Chandra Shekhar
    Chandra Shekhar was an Indian politician who briefly served as the 8th Prime Minister of India from 1990 to 1991.
  • D. Atal Bihari Vajpayee
    Atal Bihari Vajpayee was an Indian statesman, poet, and founding leader of the Bharatiya Janata Party who served three terms as Prime Minister of India.
  • E. V. P. Singh
    V. P. Singh was an Indian politician who served as the 7th Prime Minister of India and was known for implementing the Mandal Commission recommendations on reservations for backward classes.
  • 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_69d8e510fa248190b7afb274a1d4cf73 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640e92ff48190ae6e6ba2c603d5e7 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.