Triple

T22515655
Position Surface form Disambiguated ID Type / Status
Subject Tara Richards E556639 entity
Predicate givenName P17 FINISHED
Object Tara 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: Tara | Statement: [Tara Richards, givenName, Tara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tara
Context triple: [Tara Richards, givenName, Tara]
  • A. Tara
    Tara is a revered Buddhist goddess associated with compassion and protection, widely worshipped across South and Southeast Asia.
  • B. Tara
    Tara is a small rural town in Queensland, Australia, known for its agricultural community and location within the Western Downs Region.
  • C. Tara
    Tara is a central character in Anita Desai’s novel "Clear Light of Day," whose experiences reflect themes of family tension, memory, and the passage of time in post-partition India.
  • D. Tara
    Tara is a prominent figure in the Indian epic Ramayana, known as the wise and devoted wife of the vanara king Vali and later a respected queen and counselor in Kishkindha.
  • E. Tara chosen
    Tara is a female given name commonly used in English-speaking countries, often associated with notable figures such as Olympic figure skater Tara Lipinski.
  • 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_69e11e5657e881909f16ca58352c50da completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15e2cfc908190b3489228a1997f45 completed April 29, 2026, 1:26 a.m.
Created at: April 16, 2026, 8:50 p.m.