Triple

T4444544
Position Surface form Disambiguated ID Type / Status
Subject Vidyavati Kaur E96249 entity
Predicate spouse P13 FINISHED
Object Kishan Singh Sandhu E95595 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: Kishan Singh Sandhu | Statement: [Vidyavati Kaur, spouse, Kishan Singh Sandhu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kishan Singh Sandhu
Context triple: [Vidyavati Kaur, spouse, Kishan Singh Sandhu]
  • A. Kishan Singh Sandhu chosen
    Kishan Singh Sandhu was an Indian revolutionary and political activist best known as the father of freedom fighter Bhagat Singh.
  • B. Gurdial Singh
    Gurdial Singh was a prominent Indian Punjabi novelist and short story writer known for his realistic portrayals of rural life and marginalized communities.
  • C. Sher Singh
    Sher Singh was a 19th-century Maharaja of the Sikh Empire who briefly ruled Punjab during the turbulent period following Maharaja Ranjit Singh’s death.
  • D. Satwant Singh
    Satwant Singh was one of the Sikh bodyguards who assassinated Indian Prime Minister Indira Gandhi in 1984, an event that triggered widespread anti-Sikh riots across India.
  • E. Satinder Singh
    Satinder Singh is a computer scientist and researcher known for his contributions to reinforcement learning and artificial intelligence.
  • 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_69b345415ba481908df738e7174448ba completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b355d00c288190a4f3fec29b5d85b2 completed March 13, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69b613850eb88190b689a632b0e2b374 completed March 15, 2026, 2:03 a.m.
Created at: March 12, 2026, 11:32 p.m.