Triple

T2132594
Position Surface form Disambiguated ID Type / Status
Subject Chancellery of the Prime Minister, Warsaw E46574 entity
Predicate shortName P43 FINISHED
Object KPRM
KPRM is the commonly used abbreviation for the Chancellery of the Prime Minister of Poland, the central office supporting the head of government.
E237934 NE FINISHED

How this triple was built (4 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: KPRM | Statement: [Chancellery of the Prime Minister, Warsaw, shortName, KPRM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KPRM
Context triple: [Chancellery of the Prime Minister, Warsaw, shortName, KPRM]
  • A. KPAM
    KPAM is the ICAO airport code for Tyndall Air Force Base, a United States Air Force installation near Panama City, Florida.
  • B. KPRF
    KPRF is the commonly used abbreviation for the Communist Party of the Russian Federation, a major left-wing political party and principal successor to the Soviet-era Communist Party.
  • C. KAP
    KAP is the ICAO airline designator used to identify Cape Air in international aviation operations.
  • D. KP
    KP is the commonly used abbreviation for Khyber Pakhtunkhwa, a province in northwestern Pakistan known for its mountainous terrain and diverse ethnic communities.
  • E. PRU
    PRU is the stock ticker symbol for Prudential Financial, a major U.S.-based financial services and insurance company.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KPRM
Triple: [Chancellery of the Prime Minister, Warsaw, shortName, KPRM]
Generated description
KPRM is the commonly used abbreviation for the Chancellery of the Prime Minister of Poland, the central office supporting the head of government.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KPRM
Target entity description: KPRM is the commonly used abbreviation for the Chancellery of the Prime Minister of Poland, the central office supporting the head of government.
  • A. KPAM
    KPAM is the ICAO airport code for Tyndall Air Force Base, a United States Air Force installation near Panama City, Florida.
  • B. KPRF
    KPRF is the commonly used abbreviation for the Communist Party of the Russian Federation, a major left-wing political party and principal successor to the Soviet-era Communist Party.
  • C. KAP
    KAP is the ICAO airline designator used to identify Cape Air in international aviation operations.
  • D. KP
    KP is the commonly used abbreviation for Khyber Pakhtunkhwa, a province in northwestern Pakistan known for its mountainous terrain and diverse ethnic communities.
  • E. PRU
    PRU is the stock ticker symbol for Prudential Financial, a major U.S.-based financial services and insurance company.
  • F. None of above. chosen

Provenance (5 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_69a88a1626548190ae59a5028c3baa8e completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbb7b13ac819094d43159fff984cf completed March 7, 2026, 5:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae51a82a7c8190bc6737034d01f176 completed March 9, 2026, 4:50 a.m.
NEDg Description generation batch_69ae528634608190bf10e3abf5a2c2d9 completed March 9, 2026, 4:54 a.m.
NED2 Entity disambiguation (via description) batch_69ae536431bc8190b9f293d74046cb27 completed March 9, 2026, 4:58 a.m.
Created at: March 4, 2026, 7:44 p.m.