Triple

T2621074
Position Surface form Disambiguated ID Type / Status
Subject Gujarati people E59007 entity
Predicate historicalRegion P915 FINISHED
Object Saurashtra E149022 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: Saurashtra | Statement: [Gujarati people, historicalRegion, Saurashtra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saurashtra
Context triple: [Gujarati people, historicalRegion, Saurashtra]
  • A. Saurashtra State chosen
    Saurashtra State was a former state in western India formed after independence by merging numerous princely states on the Kathiawar peninsula, later integrated into the modern state of Gujarat.
  • B. Khandesh
    Khandesh is a historical region in northwestern Maharashtra, India, known for its distinct cultural identity and fertile agricultural plains along the Tapi River.
  • C. Konkan
    Konkan is a rugged, coastal region along the western shoreline of India, known for its distinctive culture, cuisine, and scenic Arabian Sea beaches.
  • D. Hadoti
    Hadoti is a cultural and geographic region in southeastern Rajasthan, India, known for its historic cities like Kota and Bundi and its distinctive Hadoti dialect of Rajasthani.
  • E. Maharashtri
    Maharashtri is an ancient Middle Indo-Aryan language, a major literary Prakrit historically used in parts of western and central 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_69ab4ac558388190962492cd2e1b0ce6 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8993c4481908fecdb235e4e731c completed March 7, 2026, 7:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa04b00908190b42f0ed753009c42 completed March 10, 2026, 4:38 a.m.
Created at: March 6, 2026, 9:50 p.m.