Triple

T19632700
Position Surface form Disambiguated ID Type / Status
Subject Goan Catholic E471310 entity
Predicate language P15 FINISHED
Object Goan Konkani 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: Goan Konkani | Statement: [Goan Catholic, language, Goan Konkani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Goan Konkani
Context triple: [Goan Catholic, language, Goan Konkani]
  • A. Konkani chosen
    Konkani is an Indo-Aryan language spoken primarily along India’s Konkan coast, especially in Goa and parts of Karnataka and Maharashtra.
  • B. Goan Portuguese
    Goan Portuguese is a regional variety of Portuguese historically spoken in Goa, India, shaped by centuries of contact with local Konkani and Indian languages.
  • C. Marathi–Konkani languages
    Marathi–Konkani languages are a group of closely related Indo-Aryan languages and dialects spoken primarily along India’s western coastal region, especially in Maharashtra, Goa, and parts of Karnataka.
  • D. Tulu
    Tulu is a Dravidian language spoken primarily in the coastal regions of Karnataka and northern Kerala in southwestern India, known for its rich oral traditions and distinct cultural identity.
  • E. Manipravalam
    Manipravalam is a medieval South Indian literary style that blends Sanskrit and regional Dravidian languages, notably used in classical dance and devotional poetry.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e6410449ec8190b8c20c0e09cd9156 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.