Triple

T23253068
Position Surface form Disambiguated ID Type / Status
Subject Shyamala Gopalan Harris E581787 entity
Predicate familyName P18 FINISHED
Object Gopalan 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: Gopalan | Statement: [Shyamala Gopalan Harris, familyName, Gopalan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gopalan
Context triple: [Shyamala Gopalan Harris, familyName, Gopalan]
  • A. Gopalan chosen
    Gopalan is an Indian-origin surname notably associated with Shyamala Gopalan, a cancer researcher and mother of U.S. Vice President Kamala Harris.
  • B. Jethmalani
    Jethmalani is an Indian surname most prominently associated with the late Ram Jethmalani, a renowned lawyer, politician, and former Union Minister of India.
  • C. Dhurjati
    Dhurjati was a prominent Telugu poet of the Vijayanagara Empire, renowned for his devotional works dedicated to Lord Shiva.
  • D. Gopal
    Gopal is the given name of Gopal Krishna Gokhale, a prominent Indian political leader and social reformer of the early 20th century.
  • E. Chandrakant
    Chandrakant is an Indian given name commonly used for men, derived from Sanskrit and often associated with the moon or “beloved of the moon.”
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f840dc819098e52272abefe616 completed April 29, 2026, 5:15 a.m.
Created at: April 17, 2026, 4:11 p.m.