Triple

T1802657
Position Surface form Disambiguated ID Type / Status
Subject Tamil people E39754 entity
Predicate classicalLiterature P6519 FINISHED
Object Sangam literature E39751 NE FINISHED

How this triple was built (3 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: Sangam literature | Statement: [Tamil people, classicalLiterature, Sangam literature]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sangam literature
Context triple: [Tamil people, classicalLiterature, Sangam literature]
  • A. Sangam literature chosen
    Sangam literature is an ancient body of classical Tamil poetry and prose, composed by numerous poets between roughly 300 BCE and 300 CE, renowned for its rich depictions of love, war, and society in early South India.
  • B. Smriti literature
    Smriti literature is a body of post-Vedic Hindu texts, including legal, ethical, and social codes such as the Dharmashastras, that guide religious practice and daily life.
  • C. Tamil literature
    Tamil literature is the body of written and oral works in the Tamil language, encompassing ancient Sangam poetry, devotional hymns, classical epics, and modern writings that reflect the culture and history of Tamil-speaking people.
  • D. Indian literature
    Indian literature is the diverse body of written and oral works produced in the many languages and cultural traditions of the Indian subcontinent, spanning ancient epics and religious texts to modern poetry, fiction, and drama.
  • E. Telugu literature
    Telugu literature is the body of written and oral works in the Telugu language, renowned for its classical poetry, epics, and rich literary tradition dating back over a millennium.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: classicalLiterature
Context triple: [Tamil people, classicalLiterature, Sangam literature]
  • A. literaryTradition
    Indicates a relationship where a work, practice, or expression belongs to, arises from, or participates in a particular established body of literary customs, styles, or conventions.
  • B. inLiterature
    Indicates that a work, concept, or entity is mentioned, discussed, or represented within a piece of literature.
  • C. ancientLanguages
    Indicates that the related entities are languages that originated in and were used during ancient historical periods.
  • D. mainClassicalLanguage chosen
    Indicates the primary classical (historically foundational) language associated with an entity, such as a text, culture, or scholarly tradition.
  • E. literaryUnit
    Indicates that one entity is a distinct segment or component (such as a chapter, scene, or passage) within a larger literary work or text.
  • F. None of above.

Provenance (4 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_69a88632aa588190ba3978fde0db5bbd completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aba67721788190951beae25e885457 completed March 7, 2026, 4:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69adb5db1c7c81908c25e62dca1cb825 completed March 8, 2026, 5:46 p.m.
PD Predicate disambiguation batch_69aa61d514c081908197ac1f7c7d7a88 completed March 6, 2026, 5:10 a.m.
Created at: March 4, 2026, 7:32 p.m.