Triple

T294432
Position Surface form Disambiguated ID Type / Status
Subject Gare du Nord E6061 entity
Predicate hasIATAcode P2569 FINISHED
Object XPG
XPG is the IATA station code for Paris Gare du Nord, one of the main international railway hubs in Paris, France.
E37923 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: XPG | Statement: [Gare du Nord, hasIATAcode, XPG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: XPG
Context triple: [Gare du Nord, hasIATAcode, XPG]
  • A. Buffalo Bell
    Buffalo Bell is a female buffalo mascot character for the Japanese professional baseball team Orix Buffaloes.
  • B. Cree
    The Cree are one of the largest Indigenous peoples of North America, with communities primarily in Canada and a rich cultural heritage including distinct Algonquian languages and traditions.
  • C. Onex
    Onex is a suburban municipality in western Switzerland located just outside the city of Geneva.
  • D. ExCom
    ExCom is the Executive Committee of the UNHCR High Commissioner’s Programme, the main intergovernmental body that advises on and approves the agency’s policies and budget for refugee protection and assistance.
  • E. Group of Five
    The Group of Five refers to the five NCAA Division I FBS football conferences outside the traditional power conferences, generally considered to have less financial resources, media exposure, and competitive depth.
  • 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: XPG
Triple: [Gare du Nord, hasIATAcode, XPG]
Generated description
XPG is the IATA station code for Paris Gare du Nord, one of the main international railway hubs in Paris, France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: XPG
Target entity description: XPG is the IATA station code for Paris Gare du Nord, one of the main international railway hubs in Paris, France.
  • A. Buffalo Bell
    Buffalo Bell is a female buffalo mascot character for the Japanese professional baseball team Orix Buffaloes.
  • B. Cree
    The Cree are one of the largest Indigenous peoples of North America, with communities primarily in Canada and a rich cultural heritage including distinct Algonquian languages and traditions.
  • C. Onex
    Onex is a suburban municipality in western Switzerland located just outside the city of Geneva.
  • D. ExCom
    ExCom is the Executive Committee of the UNHCR High Commissioner’s Programme, the main intergovernmental body that advises on and approves the agency’s policies and budget for refugee protection and assistance.
  • E. Group of Five
    The Group of Five refers to the five NCAA Division I FBS football conferences outside the traditional power conferences, generally considered to have less financial resources, media exposure, and competitive depth.
  • 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_69a2e79114b081909490b3bf5a5dbb51 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2e978420881908488df342a7d5e90 completed Feb. 28, 2026, 1:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3a5d514388190ac0f748a406ae43e completed March 1, 2026, 2:35 a.m.
NEDg Description generation batch_69a3a63b33408190bea3a099165d1233 completed March 1, 2026, 2:36 a.m.
NED2 Entity disambiguation (via description) batch_69a3a69b4e488190ae092d6989c75556 completed March 1, 2026, 2:38 a.m.
Created at: Feb. 28, 2026, 1:06 p.m.