Triple

T17951369
Position Surface form Disambiguated ID Type / Status
Subject Kashyapa E448838 entity
Predicate spouse P13 FINISHED
Object Sarama 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: Sarama | Statement: [Kashyapa, spouse, Sarama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarama
Context triple: [Kashyapa, spouse, Sarama]
  • A. Sarama chosen
    Sarama is a character in the Hindu epic Ramayana, known as the wise and loyal wife of Vibhishana who aids Sita during her captivity in Lanka.
  • B. Domba
    The Domba are a traditionally itinerant ethnic group of South Asian origin, often associated with peripatetic trades and sometimes linked historically to the ancestors of the Romani people.
  • C. Saru
    Saru is a Kelpien Starfleet officer in Star Trek: Discovery, known for his cautious nature, strong moral compass, and eventual rise to command.
  • D. Sittas
    Sittas was a prominent Byzantine general and close associate of Emperor Justinian I, noted for his campaigns against the Sassanid Persians and other foes in the early 6th century.
  • E. The Cattle
    The Cattle is the English title of Surah Al-An'am, the sixth chapter of the Qur’an, which focuses on themes of monotheism, divine guidance, and the refutation of idolatry.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afac95048190a5d1ef012899c62b completed April 19, 2026, 10:34 a.m.
Created at: April 10, 2026, 10:21 a.m.