Triple

T15969135
Position Surface form Disambiguated ID Type / Status
Subject Akananuru E387273 entity
Predicate partOf P40 FINISHED
Object Ettuthokai E202399 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: Ettuthokai | Statement: [Akananuru, partOf, Ettuthokai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ettuthokai
Context triple: [Akananuru, partOf, Ettuthokai]
  • A. Ettuthokai chosen
    Ettuthokai is a classical Tamil anthology comprising eight collections of early Sangam poems that are central to ancient Tamil literature.
  • B. Kalithokai
    Kalithokai is an ancient Tamil poetic anthology, renowned as one of the classical Sangam literature collections.
  • C. Urapakkam
    Urapakkam is a rapidly developing suburban residential area on the outskirts of Chennai in Tamil Nadu, India.
  • D. Kiasutha
    Kiasutha is an alternative name for Guyasuta, a prominent 18th-century Seneca leader and diplomat involved in key events of the French and Indian War and early American history.
  • E. Khoiniki
    Khoiniki is a town in southeastern Belarus known for its proximity to the Chernobyl-affected areas and its role in regional administration and services.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1572847f08190830e30125e829766 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe88fa308190942d37cf67458396 completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:54 a.m.