Triple

T19597563
Position Surface form Disambiguated ID Type / Status
Subject Aluva taluk E470385 entity
Predicate containsSettlement P847 FINISHED
Object Mattoor 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: Mattoor | Statement: [Aluva taluk, containsSettlement, Mattoor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mattoor
Context triple: [Aluva taluk, containsSettlement, Mattoor]
  • A. Mattoor chosen
    Mattoor is a locality in the Indian state of Kerala known for housing the historic Thiru Vellaman Thulli Siva Temple.
  • B. Angamaly
    Angamaly is a town in the Ernakulam district of Kerala, India, known as a major transportation hub and gateway to the nearby Cochin International Airport.
  • C. Thekkumkur
    Thekkumkur was a small erstwhile kingdom in the Kerala region of South India that later became part of the expanding Travancore state.
  • D. Ponnani
    Ponnani is a historic coastal town and former trading port in the Malabar region of Kerala, India, known for its cultural and religious significance, especially in Islamic scholarship.
  • E. Vadakkumkur
    Vadakkumkur was a small feudal kingdom in the Kerala region of India that later became part of the expanding Travancore state.
  • 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_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e6407c52c081908704d3a4dd6e853b completed April 20, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:43 p.m.