Triple

T17523479
Position Surface form Disambiguated ID Type / Status
Subject Siem Reap International Airport E426734 entity
Predicate iataCode P2569 FINISHED
Object REP
REP is the IATA airport code for Siem Reap International Airport, the main air gateway to Cambodia’s Angkor Wat region.
E1274468 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: REP | Statement: [Siem Reap International Airport, iataCode, REP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: REP
Context triple: [Siem Reap International Airport, iataCode, REP]
  • A. RP
    RP is the former IATA airline designator assigned to Chautauqua Airlines, a now-defunct regional carrier in the United States.
  • B. RP
    RP is the prestige British English accent traditionally associated with educated speakers and national broadcasters in the United Kingdom.
  • C. RE
    RE is the commonly used abbreviation for Rugby Europe, the governing body for rugby union in Europe.
  • D. RE
    RE is the two-letter ISO 3166-1 alpha-2 country code assigned to the French overseas department and region of Réunion.
  • E. RE
    RE is a centrist, pro-European French political party founded by Emmanuel Macron and formerly known as La République En Marche!.
  • 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: REP
Triple: [Siem Reap International Airport, iataCode, REP]
Generated description
REP is the IATA airport code for Siem Reap International Airport, the main air gateway to Cambodia’s Angkor Wat region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: REP
Target entity description: REP is the IATA airport code for Siem Reap International Airport, the main air gateway to Cambodia’s Angkor Wat region.
  • A. RP
    RP is the prestige British English accent traditionally associated with educated speakers and national broadcasters in the United Kingdom.
  • B. RP
    RP is the former IATA airline designator assigned to Chautauqua Airlines, a now-defunct regional carrier in the United States.
  • C. RE
    RE is the commonly used abbreviation for Rugby Europe, the governing body for rugby union in Europe.
  • D. RE
    RE is the two-letter ISO 3166-1 alpha-2 country code assigned to the French overseas department and region of Réunion.
  • E. RE
    RE is a centrist, pro-European French political party founded by Emmanuel Macron and formerly known as La République En Marche!.
  • 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e452d4db60819096a03dbc4254850f completed April 19, 2026, 3:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01c9452ab08190a0539964b1b90f86 completed May 11, 2026, 12:19 p.m.
NEDg Description generation batch_6a01cabea2b48190a690b17a88d45b40 completed May 11, 2026, 12:25 p.m.
NED2 Entity disambiguation (via description) batch_6a01cefa08f8819086cb86ce22193baa completed May 11, 2026, 12:43 p.m.
Created at: April 10, 2026, 5:49 a.m.