Triple

T15708940
Position Surface form Disambiguated ID Type / Status
Subject Saint Helena Airport E380783 entity
Predicate IATACode P418 FINISHED
Object HLE
HLE is the IATA airport code for Saint Helena Airport, the remote island’s primary air gateway in the South Atlantic Ocean.
 E1172654 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: HLE | Statement: [Saint Helena Airport, IATACode, HLE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HLE
Context triple: [Saint Helena Airport, IATACode, HLE]
  • A. HLU
    HLU is the National Rail station code for Helensburgh Upper railway station in Argyll and Bute, Scotland.
  • B. HEL
    HEL is the three-letter IATA airport code for Helsinki Airport, the main international gateway to Finland’s capital region.
  • C. EHLE
    EHLE is the ICAO airport code for Lelystad Airport in the Netherlands, a regional airport primarily serving general aviation and leisure flights.
  • D. HLC
    HLC is the three-letter National Rail station code for Helensburgh Central railway station in Scotland.
  • E. HLC
    HLC is the commonly used abbreviation for the Harvard Longwood Campus, a major Harvard University hub for medical and public health education and research in Boston.
  • 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: HLE
Triple: [Saint Helena Airport, IATACode, HLE]
Generated description
HLE is the IATA airport code for Saint Helena Airport, the remote island’s primary air gateway in the South Atlantic Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HLE
Target entity description: HLE is the IATA airport code for Saint Helena Airport, the remote island’s primary air gateway in the South Atlantic Ocean.
  • A. HLU
    HLU is the National Rail station code for Helensburgh Upper railway station in Argyll and Bute, Scotland.
  • B. HEL
    HEL is the three-letter IATA airport code for Helsinki Airport, the main international gateway to Finland’s capital region.
  • C. EHLE
    EHLE is the ICAO airport code for Lelystad Airport in the Netherlands, a regional airport primarily serving general aviation and leisure flights.
  • D. HLC
    HLC is the three-letter National Rail station code for Helensburgh Central railway station in Scotland.
  • E. HLC
    HLC is the commonly used abbreviation for the Harvard Longwood Campus, a major Harvard University hub for medical and public health education and research in Boston.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8d8b648190842c635f2ae7bfa4 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff757b7e0c81909b32aecc093c93e4 completed May 9, 2026, 5:57 p.m.
NEDg Description generation batch_69ff76deb1948190bc49825719ac97d5 completed May 9, 2026, 6:03 p.m.
NED2 Entity disambiguation (via description) batch_69ff77642ba4819095c1acc65da06135 completed May 9, 2026, 6:05 p.m.
Created at: April 10, 2026, 4:45 a.m.