Triple

T17237605
Position Surface form Disambiguated ID Type / Status
Subject Oban Airport E418403 entity
Predicate ICAOcode P419 FINISHED
Object EGEO
EGEO is the ICAO airport code for Oban Airport, a regional airfield serving the town of Oban in western Scotland.
 E1258017 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: EGEO | Statement: [Oban Airport, ICAOcode, EGEO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EGEO
Context triple: [Oban Airport, ICAOcode, EGEO]
  • A. GEO
    GEO is the three-letter ISO 3166-1 alpha-3 country code representing the nation of Georgia.
  • B. GEO
    GEO is an intergovernmental partnership that coordinates global efforts to build and improve Earth observation systems for informed environmental and societal decision-making.
  • C. GEOC
    GEOC is the commonly used abbreviation for the Division of Geochemistry, a professional group focused on the study of the chemical composition and processes of the Earth.
  • D. GEG
    GEG is the three-letter IATA airport code for Spokane International Airport in Spokane, Washington.
  • E. EGIS
    EGIS is the principal intelligence agency of Egypt, responsible for national security, foreign intelligence, and counterintelligence operations.
  • 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: EGEO
Triple: [Oban Airport, ICAOcode, EGEO]
Generated description
EGEO is the ICAO airport code for Oban Airport, a regional airfield serving the town of Oban in western Scotland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EGEO
Target entity description: EGEO is the ICAO airport code for Oban Airport, a regional airfield serving the town of Oban in western Scotland.
  • A. GEO
    GEO is the three-letter ISO 3166-1 alpha-3 country code representing the nation of Georgia.
  • B. GEO
    GEO is an intergovernmental partnership that coordinates global efforts to build and improve Earth observation systems for informed environmental and societal decision-making.
  • C. GEOC
    GEOC is the commonly used abbreviation for the Division of Geochemistry, a professional group focused on the study of the chemical composition and processes of the Earth.
  • D. GEG
    GEG is the three-letter IATA airport code for Spokane International Airport in Spokane, Washington.
  • E. EGIS
    EGIS is the principal intelligence agency of Egypt, responsible for national security, foreign intelligence, and counterintelligence operations.
  • 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dfcf2608190b6935b79ea2ae946 completed April 19, 2026, 1:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01676596a48190ae17a411b86e613e completed May 11, 2026, 5:21 a.m.
NEDg Description generation batch_6a0168a45fc881908540d142db1ed1e9 completed May 11, 2026, 5:27 a.m.
NED2 Entity disambiguation (via description) batch_6a01692c44c881908cd986ad6cf10596 completed May 11, 2026, 5:29 a.m.
Created at: April 10, 2026, 5:39 a.m.