Triple

T17362573
Position Surface form Disambiguated ID Type / Status
Subject Kandy railway station E422103 entity
Predicate hasStationCode P1289 FINISHED
Object KDY
KDY is the station code for Kandy railway station, a major rail hub in the central highlands of Sri Lanka.
E1265017 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: KDY | Statement: [Kandy railway station, hasStationCode, KDY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KDY
Context triple: [Kandy railway station, hasStationCode, KDY]
  • A. KDH
    KDH is a Slovak Christian democratic political party known for its center-right, pro-European, and socially conservative positions.
  • B. KDH
    KDH is the IATA airport code for Kandahar International Airport, a major airport serving the city of Kandahar in southern Afghanistan.
  • C. Ky
    Ky is the given name of Ky Bowman, an American professional basketball player known for his time in the NBA and overseas leagues.
  • D. KUD
    KUD is the station code used to identify Kungsträdgården metro station in the Stockholm metro system.
  • E. KND
    KND is the abbreviated name for the animated television series "Codename: Kids Next Door," which follows a group of child operatives fighting adult tyranny from their high-tech treehouse headquarters.
  • 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: KDY
Triple: [Kandy railway station, hasStationCode, KDY]
Generated description
KDY is the station code for Kandy railway station, a major rail hub in the central highlands of Sri Lanka.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KDY
Target entity description: KDY is the station code for Kandy railway station, a major rail hub in the central highlands of Sri Lanka.
  • A. KDH
    KDH is a Slovak Christian democratic political party known for its center-right, pro-European, and socially conservative positions.
  • B. KDH
    KDH is the IATA airport code for Kandahar International Airport, a major airport serving the city of Kandahar in southern Afghanistan.
  • C. Ky
    Ky is the given name of Ky Bowman, an American professional basketball player known for his time in the NBA and overseas leagues.
  • D. KUD
    KUD is the station code used to identify Kungsträdgården metro station in the Stockholm metro system.
  • E. KND
    KND is the abbreviated name for the animated television series "Codename: Kids Next Door," which follows a group of child operatives fighting adult tyranny from their high-tech treehouse headquarters.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a4e3c3481909dfaa00334c5010e completed April 19, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01956294ec819083c1dde8fc2685e4 completed May 11, 2026, 8:37 a.m.
NEDg Description generation batch_6a019b7ab6bc8190843e2c6c7f2007d7 completed May 11, 2026, 9:03 a.m.
NED2 Entity disambiguation (via description) batch_6a019c53d8b0819083f380693943f881 completed May 11, 2026, 9:07 a.m.
Created at: April 10, 2026, 5:44 a.m.