Triple

T9389065
Position Surface form Disambiguated ID Type / Status
Subject Perth Airport (Scotland) E225976 entity
Predicate hasIATAcode P2569 FINISHED
Object PSL
PSL is the IATA airport code assigned to Perth Airport in Scotland.
E796126 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: PSL | Statement: [Perth Airport (Scotland), hasIATAcode, PSL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PSL
Context triple: [Perth Airport (Scotland), hasIATAcode, PSL]
  • A. PSL
    PSL is the commonly used abbreviation for the Physical Sciences Laboratory, a research facility focused on advancing knowledge and technology in the physical sciences.
  • B. PSL
    PSL is the top professional football (soccer) league system in South Africa, organizing the country’s premier club competitions.
  • C. PSL
    PSL is a professional Twenty20 cricket league in Pakistan featuring franchise teams that compete annually.
  • D. PSL
    PSL is a centrist agrarian and Christian-democratic political party in Poland known for representing rural interests and frequently participating in coalition governments.
  • E. PSL
    PSL is a prestigious French research university in Paris known for its excellence in science, humanities, and the arts.
  • 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: PSL
Triple: [Perth Airport (Scotland), hasIATAcode, PSL]
Generated description
PSL is the IATA airport code assigned to Perth Airport in Scotland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PSL
Target entity description: PSL is the IATA airport code assigned to Perth Airport in Scotland.
  • A. PSL
    PSL is the commonly used abbreviation for the Physical Sciences Laboratory, a research facility focused on advancing knowledge and technology in the physical sciences.
  • B. PSL
    PSL is the top professional football (soccer) league system in South Africa, organizing the country’s premier club competitions.
  • C. PSL
    PSL is a professional Twenty20 cricket league in Pakistan featuring franchise teams that compete annually.
  • D. PSL
    PSL is a centrist agrarian and Christian-democratic political party in Poland known for representing rural interests and frequently participating in coalition governments.
  • E. PSL
    PSL is a prestigious French research university in Paris known for its excellence in science, humanities, and the arts.
  • 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_69ca842f7e3481908bf5bcf52e032dbd completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd50d83c188190925c389dff1341b0 completed April 1, 2026, 5:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69d100f1182881909c3b11c22e911b61 completed April 4, 2026, 12:15 p.m.
NEDg Description generation batch_69d1017a36e0819091bd6d7bc75d1a97 completed April 4, 2026, 12:18 p.m.
NED2 Entity disambiguation (via description) batch_69d10270f9948190bbf937089f88bacf completed April 4, 2026, 12:22 p.m.
Created at: March 30, 2026, 7:45 p.m.