Triple

T19191987
Position Surface form Disambiguated ID Type / Status
Subject Lal Devi Mata E469861 entity
Predicate hasTitle P38 FINISHED
Object Mata 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: Mata | Statement: [Lal Devi Mata, hasTitle, Mata]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mata
Context triple: [Lal Devi Mata, hasTitle, Mata]
  • A. Mata chosen
    Mata is a title used in certain South Asian cultural and religious contexts, often signifying a revered mother figure or goddess.
  • B. Mata Leão
    Mata Leão is a studio album by the American hardcore punk band Biohazard, known for its aggressive sound and fusion of metal and hardcore elements.
  • C. Mazani
    Mazani is an alternative name for the Mazanderani language, an Iranian language spoken primarily along the southern coast of the Caspian Sea in northern Iran.
  • D. Matta
    Matta is a surname most prominently associated with Thad Matta, a successful American college basketball coach known for his tenures at Xavier and Ohio State.
  • E. Matta
    Matta is a town located in Pakistan’s Swat District, known for its agricultural surroundings and scenic mountainous landscape.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a3434881908acc4063a9ee9386 completed April 20, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:07 p.m.