Triple

T504216
Position Surface form Disambiguated ID Type / Status
Subject Hankou Railway Station E10464 entity
Predicate hasStationCode P1289 FINISHED
Object HKN
HKN is the station code for Hankou Railway Station, a major rail transport hub in Wuhan, China.
E62893 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: HKN | Statement: [Hankou Railway Station, hasStationCode, HKN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HKN
Context triple: [Hankou Railway Station, hasStationCode, HKN]
  • A. HKS
    HKS is the Harvard Kennedy School, a leading public policy and public administration graduate school at Harvard University.
  • B. HeKKSaGOn University Alliance
    HeKKSaGOn University Alliance is a strategic academic network linking leading universities in Japan and Germany to promote collaborative research, education, and innovation.
  • C. HKS, Inc.
    HKS, Inc. is a global architecture firm known for designing major sports, entertainment, and commercial venues.
  • D. KNUQ
    KNUQ is the ICAO airport code for Moffett Federal Airfield, a joint civil-military airfield located in Moffett Field, California.
  • E. HMC
    HMC is a professional association of leading independent school heads in the United Kingdom and internationally.
  • 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: HKN
Triple: [Hankou Railway Station, hasStationCode, HKN]
Generated description
HKN is the station code for Hankou Railway Station, a major rail transport hub in Wuhan, China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HKN
Target entity description: HKN is the station code for Hankou Railway Station, a major rail transport hub in Wuhan, China.
  • A. HKS
    HKS is the Harvard Kennedy School, a leading public policy and public administration graduate school at Harvard University.
  • B. HeKKSaGOn University Alliance
    HeKKSaGOn University Alliance is a strategic academic network linking leading universities in Japan and Germany to promote collaborative research, education, and innovation.
  • C. HKS, Inc.
    HKS, Inc. is a global architecture firm known for designing major sports, entertainment, and commercial venues.
  • D. KNUQ
    KNUQ is the ICAO airport code for Moffett Federal Airfield, a joint civil-military airfield located in Moffett Field, California.
  • E. HMC
    HMC is a professional association of leading independent school heads in the United Kingdom and internationally.
  • 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_69a2e848adf881908e5e04f7af030093 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f149bd1c81908ff58ac504ace2bf completed Feb. 28, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a48a7b71848190ab3e69fc84779301 completed March 1, 2026, 6:50 p.m.
NEDg Description generation batch_69a48c1329f0819093fa4eb579075243 completed March 1, 2026, 6:57 p.m.
NED2 Entity disambiguation (via description) batch_69a48c688fcc81909d79068875b89aee completed March 1, 2026, 6:58 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.