Triple

T13217060
Position Surface form Disambiguated ID Type / Status
Subject Devonport Airport E314643 entity
Predicate hasIATAcode P2569 FINISHED
Object DPO
DPO is the IATA airport code for Devonport Airport in Tasmania, Australia.
 E1028845 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: DPO | Statement: [Devonport Airport, hasIATAcode, DPO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DPO
Context triple: [Devonport Airport, hasIATAcode, DPO]
  • A. DOP
    DOP is a scholarly journal focused on Byzantine studies and related fields, published by Dumbarton Oaks Research Library and Collection.
  • B. DOP
    DOP is the common abbreviation for the Daughters of Penelope, a women’s organization affiliated with the American Hellenic Educational Progressive Association that promotes Hellenic ideals, philanthropy, and civic responsibility.
  • C. UN DPO
    The UN Department of Peace Operations (UN DPO) is the United Nations body responsible for planning, managing, and supporting peacekeeping and related field missions around the world.
  • D. DNPO
    DNPO is the ICAO airport code for Port Harcourt International Airport in Nigeria.
  • E. DPD
    DPD is the commonly used abbreviation for the "Diccionario panhispánico de dudas," a comprehensive reference work by the Royal Spanish Academy that clarifies usage, grammar, and style questions across the Spanish-speaking world.
  • 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: DPO
Triple: [Devonport Airport, hasIATAcode, DPO]
Generated description
DPO is the IATA airport code for Devonport Airport in Tasmania, Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DPO
Target entity description: DPO is the IATA airport code for Devonport Airport in Tasmania, Australia.
  • A. DOP
    DOP is the common abbreviation for the Daughters of Penelope, a women’s organization affiliated with the American Hellenic Educational Progressive Association that promotes Hellenic ideals, philanthropy, and civic responsibility.
  • B. DOP
    DOP is a scholarly journal focused on Byzantine studies and related fields, published by Dumbarton Oaks Research Library and Collection.
  • C. UN DPO
    The UN Department of Peace Operations (UN DPO) is the United Nations body responsible for planning, managing, and supporting peacekeeping and related field missions around the world.
  • D. DNPO
    DNPO is the ICAO airport code for Port Harcourt International Airport in Nigeria.
  • E. DPD
    DPD is the commonly used abbreviation for the "Diccionario panhispánico de dudas," a comprehensive reference work by the Royal Spanish Academy that clarifies usage, grammar, and style questions across the Spanish-speaking world.
  • 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_69d806aee7308190b70a237ba2a6e3e1 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98cf392e08190949ee4d194566395 completed April 10, 2026, 11:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff1ebf648190a27d11b3dc494446 completed May 3, 2026, 7:54 a.m.
NEDg Description generation batch_69f7013a368c8190a768f837f6551f5b completed May 3, 2026, 8:03 a.m.
NED2 Entity disambiguation (via description) batch_69f7038563848190ae96538e30ecafd5 completed May 3, 2026, 8:12 a.m.
Created at: April 9, 2026, 9:18 p.m.