Triple

T5855236
Position Surface form Disambiguated ID Type / Status
Subject Kamala Harris E130134 entity
Predicate givenName P17 FINISHED
Object Kamala E130134 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: Kamala | Statement: [Kamala Harris, givenName, Kamala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kamala
Context triple: [Kamala Harris, givenName, Kamala]
  • A. Kamala chosen
    Kamala is the given name of Kamala Harris, the 49th vice president of the United States and the first woman, first Black American, and first South Asian American to hold the office.
  • B. Kamala
    Kamala is a renowned Marathi play by Vijay Tendulkar that critiques the commodification of women through the story of a journalist who buys a tribal woman to expose human trafficking.
  • C. Kamala
    Kamala is a Hindu goddess associated with prosperity and the tantric form of Lakshmi, revered as one of the ten Mahavidyas.
  • D. Leona Woods
    Leona Woods was an American physicist who, as one of the few women on the Manhattan Project, played a key role in the development and operation of the first nuclear reactor.
  • E. Sadiqa Kendi
    Sadiqa Kendi is an American pediatric emergency medicine physician and academic known for her work in child injury prevention and health equity.
  • 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_69c0084de39081909eb34e6bed74215a completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03554651c8190b3009d41eecf6779 completed March 22, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a1bc58d081908568294278cbf3a9 completed March 23, 2026, 2:13 a.m.
Created at: March 22, 2026, 3:55 p.m.