Triple

T5706557
Position Surface form Disambiguated ID Type / Status
Subject The Curse of Kehama E125796 entity
Predicate hasProtagonist P8706 FINISHED
Object Kailyal E539224 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: Kailyal | Statement: [The Curse of Kehama, hasProtagonist, Kailyal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kailyal
Context triple: [The Curse of Kehama, hasProtagonist, Kailyal]
  • A. Kailyal chosen
    Kailyal is a central heroine in Robert Southey’s epic poem "The Curse of Kehama," known for her steadfast virtue and endurance amid supernatural trials.
  • B. Barshaini
    Barshaini is a small Himalayan village in Himachal Pradesh, India, that serves as a popular base and trailhead for treks into the Parvati Valley and surrounding high-altitude landscapes.
  • C. Kadamtala
    Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • D. Kasarani
    Kasarani is a residential and commercial suburb in northeastern Nairobi, Kenya, known for hosting major sports and educational facilities.
  • E. Bairat
    Bairat is a historic town in Rajasthan, India, known for its ancient Buddhist archaeological remains and connections to the Mauryan period.
  • 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_69c0082d6fe48190b777fb383769e5c8 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0248751bc8190b12aaa42d1ef17e3 completed March 22, 2026, 5:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07de7df8c8190824d24f729eaa04d completed March 22, 2026, 11:40 p.m.
Created at: March 22, 2026, 3:45 p.m.