Triple

T8549613
Position Surface form Disambiguated ID Type / Status
Subject Ancient Tamilakam E202412 entity
Predicate majorLiteraryTradition P2989 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: [Ancient Tamilakam, majorLiteraryTradition, Sangam literature]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sangam literature
Context triple: [Ancient Tamilakam, majorLiteraryTradition, 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. Sanskrit literature
    Sanskrit literature is the body of ancient and classical texts composed in the Sanskrit language, encompassing religious scriptures, epic poetry, philosophy, and scholarly works that have profoundly shaped South Asian culture and thought.
  • C. Vijayanagara literature
    Vijayanagara literature refers to the rich body of mainly Telugu, Kannada, and Sanskrit works produced under the patronage of the Vijayanagara Empire, noted for its devotional, courtly, and classical poetic traditions.
  • D. 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.
  • E. Dravidian literature
    Dravidian literature is the body of written and oral works produced in the Dravidian languages of South India and surrounding regions, encompassing ancient, medieval, and modern traditions across languages such as Tamil, Telugu, Kannada, and Malayalam.
  • 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: majorLiteraryTradition
Context triple: [Ancient Tamilakam, majorLiteraryTradition, Sangam literature]
  • A. literaryTradition chosen
    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. literaryMovement
    Indicates the artistic or intellectual movement in literature with which a work, author, or text is associated or to which it belongs.
  • C. writingTradition
    Indicates a relationship where an entity is associated with, follows, or belongs to a particular system or style of written expression or script usage.
  • D. readingTradition
    Indicates a relationship where a text, work, or practice is transmitted, interpreted, and maintained through an established history of readings or interpretive practices.
  • E. literarySubject
    Indicates that one entity serves as the subject, topic, or focus of a literary work created by another entity.
  • 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_69ca832610e08190b3b6c6cd2c250255 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe753d3608190b0573477182cf194 completed March 31, 2026, 3:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef318417881908619e137f22c6b74 completed April 2, 2026, 10:52 p.m.
PD Predicate disambiguation batch_69cbd113e05c81908f4f3fc1b5925164 completed March 31, 2026, 1:50 p.m.
Created at: March 30, 2026, 6:19 p.m.