Triple

T13392031
Position Surface form Disambiguated ID Type / Status
Subject Memorial Park station E319597 entity
Predicate hasStationCode P1289 FINISHED
Object MPPK
MPPK is the station code for Memorial Park station, a public transit stop serving passengers under that designation.
E1036472 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: MPPK | Statement: [Memorial Park station, hasStationCode, MPPK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MPPK
Context triple: [Memorial Park station, hasStationCode, MPPK]
  • A. MPP
    MPP is a leading German research institute focused on fundamental physics, particularly particle and astroparticle physics, within the Max Planck Society.
  • B. MPP
    MPP is the abbreviation commonly used for the Mongolian People's Party, a major political party in Mongolia.
  • C. MPP
    MPP is the commonly used acronym for New Zealand’s Ministry for Pacific Peoples, the government agency responsible for policies and services relating to Pacific communities in Aotearoa New Zealand.
  • D. MPPA
    MPPA is the ICAO airport code for Panama Pacifico International Airport, a commercial airport serving the Panama City area in Panama.
  • E. PKKP
    PKKP is the abbreviation for Polska Krajowa Kasa Pożyczkowa, a historical Polish national loan office that played a key role in the country’s early financial and monetary system.
  • 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: MPPK
Triple: [Memorial Park station, hasStationCode, MPPK]
Generated description
MPPK is the station code for Memorial Park station, a public transit stop serving passengers under that designation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MPPK
Target entity description: MPPK is the station code for Memorial Park station, a public transit stop serving passengers under that designation.
  • A. MPP
    MPP is the abbreviation commonly used for the Mongolian People's Party, a major political party in Mongolia.
  • B. MPP
    MPP is a leading German research institute focused on fundamental physics, particularly particle and astroparticle physics, within the Max Planck Society.
  • C. MPP
    MPP is the commonly used acronym for New Zealand’s Ministry for Pacific Peoples, the government agency responsible for policies and services relating to Pacific communities in Aotearoa New Zealand.
  • D. MPPA
    MPPA is the ICAO airport code for Panama Pacifico International Airport, a commercial airport serving the Panama City area in Panama.
  • E. PKKP
    PKKP is the abbreviation for Polska Krajowa Kasa Pożyczkowa, a historical Polish national loan office that played a key role in the country’s early financial and monetary system.
  • 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_69d806b886bc8190b676e7768b8e01c5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dba0d74e5881909828854bba7d9a87 completed April 12, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f72693a440819095a3136d8f49680a completed May 3, 2026, 10:42 a.m.
NEDg Description generation batch_69f72751f1b48190a8a79f10bf52b73d completed May 3, 2026, 10:45 a.m.
NED2 Entity disambiguation (via description) batch_69f727fbfde88190865aea5d6b4cb29d completed May 3, 2026, 10:48 a.m.
Created at: April 9, 2026, 9:34 p.m.