Triple

T7120154
Position Surface form Disambiguated ID Type / Status
Subject Park Street metro station E165927 entity
Predicate hasStationCode P1289 FINISHED
Object PKS
PKS is the station code for Park Street, a major metro station in Kolkata, India.
 E643875 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: PKS | Statement: [Park Street metro station, hasStationCode, PKS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PKS
Context triple: [Park Street metro station, hasStationCode, PKS]
  • A. PKX
    PKX is the IATA airport code for Beijing Daxing International Airport, a major international aviation hub serving Beijing, China.
  • B. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • C. PK
    PK is a music producer best known for his work on DMX's influential debut album "It's Dark and Hell Is Hot."
  • D. PK
    PK is a compact bitmap font file format traditionally used by TeX systems to store rasterized glyphs generated from METAFONT sources.
  • E. PKB
    PKB is the IATA airport code for Mid-Ohio Valley Regional Airport serving the Parkersburg–Vienna area in West Virginia, USA.
  • 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: PKS
Triple: [Park Street metro station, hasStationCode, PKS]
Generated description
PKS is the station code for Park Street, a major metro station in Kolkata, India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PKS
Target entity description: PKS is the station code for Park Street, a major metro station in Kolkata, India.
  • A. PKX
    PKX is the IATA airport code for Beijing Daxing International Airport, a major international aviation hub serving Beijing, China.
  • B. PK
    PK is a music producer best known for his work on DMX's influential debut album "It's Dark and Hell Is Hot."
  • C. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • D. PK
    PK is a compact bitmap font file format traditionally used by TeX systems to store rasterized glyphs generated from METAFONT sources.
  • E. PKB
    PKB is the IATA airport code for Mid-Ohio Valley Regional Airport serving the Parkersburg–Vienna area in West Virginia, USA.
  • 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_69c6888227bc8190a1394679e3116f90 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e61ca6a88190a0eb9f287e3b723c completed March 27, 2026, 8:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7a32870e481909472f8fcd2501289 completed March 28, 2026, 9:45 a.m.
NEDg Description generation batch_69c7a390cf6c8190902bdfd0ff536093 completed March 28, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_69c7a4be1cbc8190a7e4eb91d604f994 completed March 28, 2026, 9:51 a.m.
Created at: March 27, 2026, 2:43 p.m.