Triple

T20567543
Position Surface form Disambiguated ID Type / Status
Subject Majelis Permusyawaratan Rakyat E505002 entity
Predicate shortName P43 FINISHED
Object MPR 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: MPR | Statement: [Majelis Permusyawaratan Rakyat, shortName, MPR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MPR
Context triple: [Majelis Permusyawaratan Rakyat, shortName, MPR]
  • A. MPR chosen
    MPR is the Indonesian acronym for the People's Consultative Assembly, the country's highest constitutional body responsible for key legislative and constitutional functions.
  • B. MPRT
    MPRT is the Swedish Press and Broadcasting Authority responsible for supervising and regulating press, radio, and television in Sweden.
  • C. MMPR
    MMPR is the ICAO airport code for Licenciado Gustavo Díaz Ordaz International Airport serving Puerto Vallarta, Mexico.
  • D. MP
    MP is the vehicle registration code for the Indian state of Madhya Pradesh.
  • E. MP
    MP is the two-letter ISO 3166-1 alpha-2 country code assigned to the Northern Mariana Islands.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a33f7c8190966da03528dfe8aa completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.