Triple

T12531805
Position Surface form Disambiguated ID Type / Status
Subject Olympic Air E299586 entity
Predicate IATAcode P418 FINISHED
Object OA
OA is the IATA airline designator assigned to Olympic Air, a Greek regional airline.
 E988436 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: OA | Statement: [Olympic Air, IATAcode, OA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: OA
Context triple: [Olympic Air, IATAcode, OA]
  • A. OA
    OA is the abbreviated name for the Office of Audit, a governmental or institutional body responsible for conducting audits and evaluations to ensure accountability and proper use of resources.
  • B. Directory of Open Access Journals
    The Directory of Open Access Journals (DOAJ) is an online index that curates and provides access to high-quality, peer-reviewed open access scholarly journals from around the world.
  • C. ORS
    ORS is the commonly used abbreviation for the Oregon Revised Statutes, the codified laws governing the U.S. state of Oregon.
  • D. OAI
    OAI is the commonly used abbreviation for the OpenAPI Initiative, an open governance organization that standardizes the OpenAPI Specification for describing RESTful APIs.
  • E. OAI
    OAI is the Office of Anticorruption and Integrity, a body typically responsible for promoting transparency, preventing corruption, and ensuring ethical conduct within an organization or institution.
  • 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: OA
Triple: [Olympic Air, IATAcode, OA]
Generated description
OA is the IATA airline designator assigned to Olympic Air, a Greek regional airline.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: OA
Target entity description: OA is the IATA airline designator assigned to Olympic Air, a Greek regional airline.
  • A. OA
    OA is the abbreviated name for the Office of Audit, a governmental or institutional body responsible for conducting audits and evaluations to ensure accountability and proper use of resources.
  • B. Directory of Open Access Journals
    The Directory of Open Access Journals (DOAJ) is an online index that curates and provides access to high-quality, peer-reviewed open access scholarly journals from around the world.
  • C. ORS
    ORS is the commonly used abbreviation for the Oregon Revised Statutes, the codified laws governing the U.S. state of Oregon.
  • D. OAI
    OAI is the commonly used abbreviation for the OpenAPI Initiative, an open governance organization that standardizes the OpenAPI Specification for describing RESTful APIs.
  • E. OAI
    OAI is the Office of Anticorruption and Integrity, a body typically responsible for promoting transparency, preventing corruption, and ensuring ethical conduct within an organization or institution.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95469d100819087c83bc55e3ec9ce completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc8866c81908821525b595715e2 completed May 2, 2026, 7:08 p.m.
NEDg Description generation batch_69f64da25bf88190889273bf41e2f154 completed May 2, 2026, 7:16 p.m.
NED2 Entity disambiguation (via description) batch_69f65213ed84819086fda178aaf9e774 completed May 2, 2026, 7:35 p.m.
Created at: April 8, 2026, 9:57 p.m.