Triple

T20272933
Position Surface form Disambiguated ID Type / Status
Subject Discover Airlines E502935 entity
Predicate ICAOCode P419 FINISHED
Object OCN
OCN is the ICAO airline designator assigned to Discover Airlines, a German leisure carrier operated by the Lufthansa Group.
E1422197 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: OCN | Statement: [Discover Airlines, ICAOCode, OCN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OCN
Context triple: [Discover Airlines, ICAOCode, OCN]
  • A. OCN
    OCN is the IATA airport code for Oceanside Municipal Airport, a public general aviation facility in Oceanside, California.
  • B. OCS
    OCS (Online Charging System) is a real-time telecommunications billing platform that manages and rates service usage, often working with PCRF to enforce charging and policy decisions.
  • C. OCS
    OCS is a U.S. federal agency within the Administration for Children and Families that administers programs to reduce poverty, promote self-sufficiency, and strengthen communities.
  • D. OCS
    OCS is a French subscription television network and streaming service known for broadcasting premium series and films, including international productions.
  • E. OCS
    OCS is a United States Marine Corps training program that evaluates and prepares prospective officers for commissioning.
  • 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: OCN
Triple: [Discover Airlines, ICAOCode, OCN]
Generated description
OCN is the ICAO airline designator assigned to Discover Airlines, a German leisure carrier operated by the Lufthansa Group.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: OCN
Target entity description: OCN is the ICAO airline designator assigned to Discover Airlines, a German leisure carrier operated by the Lufthansa Group.
  • A. OCN
    OCN is the IATA airport code for Oceanside Municipal Airport, a public general aviation facility in Oceanside, California.
  • B. OCS
    OCS (Online Charging System) is a real-time telecommunications billing platform that manages and rates service usage, often working with PCRF to enforce charging and policy decisions.
  • C. OCS
    OCS is a French subscription television network and streaming service known for broadcasting premium series and films, including international productions.
  • D. OCS
    OCS (Original Chip Set) is the first-generation custom graphics and sound chipset used in early Commodore Amiga computers, providing advanced multimedia capabilities for its time.
  • E. OCS
    OCS is a U.S. federal agency within the Administration for Children and Families that administers programs to reduce poverty, promote self-sufficiency, and strengthen communities.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e675dff3c4819098ba45eba4e7b296 completed April 20, 2026, 6:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a085a1eeed881909fdda6e5e044216e completed May 16, 2026, 11:50 a.m.
NEDg Description generation batch_6a085ac5b5f4819083c4d12e9cabc758 completed May 16, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_6a085bc0781c81909fc53a83291badc0 completed May 16, 2026, 11:57 a.m.
Created at: April 16, 2026, 10:20 a.m.