Triple

T19731111
Position Surface form Disambiguated ID Type / Status
Subject Matsya kingdom E473854 entity
Predicate hasRoyalFamilyMember P68121 FINISHED
Object Sankha 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: Sankha | Statement: [Matsya kingdom, hasRoyalFamilyMember, Sankha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sankha
Context triple: [Matsya kingdom, hasRoyalFamilyMember, Sankha]
  • A. Sankha chosen
    Sankha is a relatively obscure figure from ancient Indian tradition, known primarily as the son of King Virata.
  • B. Shankhodhar
    Shankhodhar is an island off the coast of Gujarat, India, revered as the mythological residence of Lord Krishna and a significant Hindu pilgrimage site.
  • C. Sankar
    Sankar is a common Indian given name and surname, often associated with Hindu cultural and religious traditions.
  • D. Parchal
    Parchal is a town in Portugal’s Algarve region, situated near the Arade River opposite Portimão and known historically for its fishing and canning industries.
  • E. Jalandhari
    Jalandhari is a surname most prominently associated with the Pakistani poet and lyricist Hafeez Jalandhari, known for writing the lyrics of Pakistan’s national anthem.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e649fd18148190a6e85b2be0069dde completed April 20, 2026, 3:45 p.m.
Created at: April 10, 2026, 1:47 p.m.