Triple

T19939231
Position Surface form Disambiguated ID Type / Status
Subject MDMK E479259 entity
Predicate shortName P43 FINISHED
Object MDMK 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: MDMK | Statement: [MDMK, shortName, MDMK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MDMK
Context triple: [MDMK, shortName, MDMK]
  • A. MDMK chosen
    MDMK is a regional political party in the Indian state of Tamil Nadu, founded and led by Vaiko after splitting from the Dravida Munnetra Kazhagam (DMK).
  • B. DMDK
    DMDK (Desiya Murpokku Dravida Kazhagam) is a regional political party in Tamil Nadu, India, founded and led by actor-turned-politician Vijayakanth.
  • C. KMK
    KMK is the central coordinating body of Germany’s state education and cultural ministers, responsible for harmonizing policies across the federal states.
  • D. KMDT
    KMDT is the ICAO airport code for Harrisburg International Airport, a commercial airport serving the Harrisburg, Pennsylvania metropolitan area.
  • E. KMD
    KMD was an early 1990s hip-hop group known for its socially conscious, Afrocentric lyrics and for launching the career of rapper MF DOOM (then known as Zev Love X).
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a19d77c819088bce99c94568d0d completed April 20, 2026, 4:53 p.m.
Created at: April 10, 2026, 1:53 p.m.