Triple

T17088338
Position Surface form Disambiguated ID Type / Status
Subject Parkes Airport E414658 entity
Predicate IATA code P2569 FINISHED
Object PKE
PKE is the three-letter IATA airport code assigned to Parkes Airport in New South Wales, Australia.
E1249170 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: PKE | Statement: [Parkes Airport, IATA code, PKE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PKE
Context triple: [Parkes Airport, IATA code, PKE]
  • A. PK
    PK is a compact bitmap font file format traditionally used by TeX systems to store rasterized glyphs generated from METAFONT sources.
  • 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 a 2014 Indian satirical science fiction comedy film directed by Rajkumar Hirani, known for its critique of religious dogma and superstition through the story of an alien played by Aamir Khan.
  • D. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • E. PKP
    PKP is Poland’s state-owned national railway operator, responsible for much of the country’s passenger and freight rail transport infrastructure.
  • 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: PKE
Triple: [Parkes Airport, IATA code, PKE]
Generated description
PKE is the three-letter IATA airport code assigned to Parkes Airport in New South Wales, Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PKE
Target entity description: PKE is the three-letter IATA airport code assigned to Parkes Airport in New South Wales, Australia.
  • A. PK
    PK is a music producer best known for his work on DMX's influential debut album "It's Dark and Hell Is Hot."
  • B. PK
    PK is a 2014 Indian satirical science fiction comedy film directed by Rajkumar Hirani, known for its critique of religious dogma and superstition through the story of an alien played by Aamir Khan.
  • C. PK
    PK is a compact bitmap font file format traditionally used by TeX systems to store rasterized glyphs generated from METAFONT sources.
  • D. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • E. PKP
    PKP is Poland’s state-owned national railway operator, responsible for much of the country’s passenger and freight rail transport infrastructure.
  • 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbe92e488190b947287a968086d5 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012ee81fd08190a7e1f5958fbe3b97 completed May 11, 2026, 1:20 a.m.
NEDg Description generation batch_6a012ff7788c819086b2e6c0e382014c completed May 11, 2026, 1:25 a.m.
NED2 Entity disambiguation (via description) batch_6a0130dbe1f8819095b2d36882bf3287 completed May 11, 2026, 1:29 a.m.
Created at: April 10, 2026, 5:35 a.m.