Triple

T12229857
Position Surface form Disambiguated ID Type / Status
Subject Central MTR station E291444 entity
Predicate hasCode P9567 FINISHED
Object CEN
CEN is the station code for Hong Kong’s Central MTR station, a major interchange hub on the city’s rapid transit network.
E969231 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: CEN | Statement: [Central MTR station, hasCode, CEN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CEN
Context triple: [Central MTR station, hasCode, CEN]
  • A. CEN
    CEN (European Committee for Standardization) is a major European standards organization that develops and maintains voluntary technical standards to support trade, safety, and interoperability across Europe.
  • B. CEN-SAD
    CEN-SAD (Community of Sahel-Saharan States) is a regional economic community in Africa focused on promoting economic integration and cooperation among its mainly Sahel and Sahara region member states.
  • C. Cen
    Cen is the standard astronomical abbreviation for Centaurus, a prominent constellation in the southern sky.
  • D. LCEN
    LCEN is the ICAO airport code for Ercan International Airport, the main air gateway to Northern Cyprus.
  • E. CNE
    CNE is Ecuador’s National Electoral Council, the independent public authority responsible for organizing and overseeing the country’s electoral processes and guaranteeing the transparency of elections.
  • 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: CEN
Triple: [Central MTR station, hasCode, CEN]
Generated description
CEN is the station code for Hong Kong’s Central MTR station, a major interchange hub on the city’s rapid transit network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CEN
Target entity description: CEN is the station code for Hong Kong’s Central MTR station, a major interchange hub on the city’s rapid transit network.
  • A. CEN
    CEN (European Committee for Standardization) is a major European standards organization that develops and maintains voluntary technical standards to support trade, safety, and interoperability across Europe.
  • B. CEN-SAD
    CEN-SAD (Community of Sahel-Saharan States) is a regional economic community in Africa focused on promoting economic integration and cooperation among its mainly Sahel and Sahara region member states.
  • C. Cen
    Cen is the standard astronomical abbreviation for Centaurus, a prominent constellation in the southern sky.
  • D. LCEN
    LCEN is the ICAO airport code for Ercan International Airport, the main air gateway to Northern Cyprus.
  • E. CNE
    CNE is Chile’s National Energy Commission, the government body responsible for designing, coordinating, and regulating the country’s energy policy and markets.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91ca34fe88190900c8791c70948b7 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aad2d488190ba36588e3376ca1a completed May 2, 2026, 2:31 p.m.
NEDg Description generation batch_69f60bdca250819090b4b4cc84d343f4 completed May 2, 2026, 2:36 p.m.
NED2 Entity disambiguation (via description) batch_69f60cd1668881908f43d895fcfba0aa completed May 2, 2026, 2:40 p.m.
Created at: April 8, 2026, 9:51 p.m.