Triple

T3424638
Position Surface form Disambiguated ID Type / Status
Subject Transylvania E72198 entity
Predicate containsCity P294 FINISHED
Object Deva E298963 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: Deva | Statement: [Transylvania, containsCity, Deva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deva
Context triple: [Transylvania, containsCity, Deva]
  • A. Deva
    Deva is the Roman-era name for the ancient fortress and settlement that later became the modern English city of Chester.
  • B. Deva chosen
    Deva is a city in western Romania known for its historic fortress and location near the Mureș River in Transylvania.
  • C. Devi
    Devi is the supreme goddess in Hinduism, embodying the divine feminine power (Shakti) in its many forms such as Durga, Parvati, Lakshmi, and Saraswati.
  • D. Devasena
    Devasena is a Hindu goddess known as one of the wives of the war god Kartikeya, often associated with valor and divine grace.
  • E. Saartha
    Saartha is a renowned Kannada novel by S. L. Bhyrappa that explores philosophical, cultural, and spiritual themes through a journey set in ancient India.
  • 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_69ad85ae14308190bcbc25cfa0246c0b completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb97fa2d88190a79cb8c7be4b3696 completed March 8, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3547468b8819088e7c4cf3b2e2079 completed March 13, 2026, 12:04 a.m.
Created at: March 8, 2026, 3:15 p.m.