Triple

T2437132
Position Surface form Disambiguated ID Type / Status
Subject EVA Air E52986 entity
Predicate ICAOCode P419 FINISHED
Object EVA
EVA is the ICAO airline designator for EVA Air, a major Taiwanese international carrier based in Taoyuan.
E265985 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: EVA | Statement: [EVA Air, ICAOCode, EVA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EVA
Context triple: [EVA Air, ICAOCode, EVA]
  • A. EGVA
    EGVA is the ICAO airport code for RAF Fairford, a Royal Air Force station in Gloucestershire, England used primarily by the United States Air Force for bomber and airlift operations.
  • B. Egvekinot
    Egvekinot is a remote urban-type settlement and port on the coast of the Bering Sea in Russia’s Far East, serving as an important local center in the Chukotka region.
  • C. Electryon
    Electryon is a king of Mycenae in Greek mythology, known primarily as the grandfather of the hero Heracles.
  • D. Nesta
    Nesta is the middle name of legendary Jamaican reggae musician and cultural icon Bob Marley.
  • E. Antu
    Antu is a Mesopotamian sky and mother goddess, best known as the consort of the supreme god Anu in ancient Sumerian and Akkadian religion.
  • 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: EVA
Triple: [EVA Air, ICAOCode, EVA]
Generated description
EVA is the ICAO airline designator for EVA Air, a major Taiwanese international carrier based in Taoyuan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: EVA
Target entity description: EVA is the ICAO airline designator for EVA Air, a major Taiwanese international carrier based in Taoyuan.
  • A. EGVA
    EGVA is the ICAO airport code for RAF Fairford, a Royal Air Force station in Gloucestershire, England used primarily by the United States Air Force for bomber and airlift operations.
  • B. Egvekinot
    Egvekinot is a remote urban-type settlement and port on the coast of the Bering Sea in Russia’s Far East, serving as an important local center in the Chukotka region.
  • C. Electryon
    Electryon is a king of Mycenae in Greek mythology, known primarily as the grandfather of the hero Heracles.
  • D. Nesta
    Nesta is the middle name of legendary Jamaican reggae musician and cultural icon Bob Marley.
  • E. Antu
    Antu is a Mesopotamian sky and mother goddess, best known as the consort of the supreme god Anu in ancient Sumerian and Akkadian religion.
  • 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_69ab4959bcc0819083246f9fb10439e3 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc9f342e88190a430b02842ded418 completed March 7, 2026, 6:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebf7085b88190938c4eefa4380970 completed March 9, 2026, 12:39 p.m.
NEDg Description generation batch_69aec30189d081908bb6865937aff20d completed March 9, 2026, 12:54 p.m.
NED2 Entity disambiguation (via description) batch_69aec39bb6a4819084652814e18f60d4 completed March 9, 2026, 12:56 p.m.
Created at: March 6, 2026, 9:43 p.m.