Triple

T20145911
Position Surface form Disambiguated ID Type / Status
Subject Baba Gurdit Singh E491301 entity
Predicate givenName P17 FINISHED
Object Gurdit 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: Gurdit | Statement: [Baba Gurdit Singh, givenName, Gurdit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gurdit
Context triple: [Baba Gurdit Singh, givenName, Gurdit]
  • A. Gurdit chosen
    Gurdit is the given name of Baba Gurdit Singh, a prominent Sikh activist best known for chartering the Komagata Maru in 1914 to challenge racist immigration laws in Canada.
  • B. Gurdev
    Gurdev is the given name of Gurdev Khush, a prominent Indian-American agronomist and plant breeder known for his contributions to the Green Revolution.
  • C. Guhilot
    Guhilot is a prominent Rajput clan historically associated with the rulers of Mewar in present-day Rajasthan, India.
  • D. Sardara
    Sardara is a small town and comune in the Province of South Sardinia, Italy, known for its thermal baths and archaeological sites.
  • E. Barindar
    Barindar is a personal name, likely a variant spelling of the name Barindra used in similar cultural or linguistic contexts.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6679e43a48190b3a5da5710b07ff7 completed April 20, 2026, 5:51 p.m.
Created at: April 11, 2026, 11:33 p.m.