Triple

T7248747
Position Surface form Disambiguated ID Type / Status
Subject Japanese domestic airport network E156540 entity
Predicate servedBy P82 FINISHED
Object AIRDO
AIRDO is a Japanese regional airline based in Hokkaido that operates domestic flights connecting Hokkaido with major cities across Japan.
 E651176 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: AIRDO | Statement: [Japanese domestic airport network, servedBy, AIRDO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AIRDO
Context triple: [Japanese domestic airport network, servedBy, AIRDO]
  • A. airag
    Airag is a traditional Mongolian fermented mare’s milk drink, mildly alcoholic and sour, commonly consumed during cultural events and daily life on the steppe.
  • B. Airok
    Airok is a small settlement located on Ailinglaplap Atoll in the Marshall Islands.
  • C. AARI
    AARI is a Russian polar research institute that leads and coordinates the country’s scientific activities in the Arctic and Antarctic regions.
  • D. Aari
    Aari is an Omotic language spoken primarily by the Aari people in southwestern Ethiopia.
  • E. ARO
    ARO is the U.S. Army Research Office, a primary Army organization that funds and manages basic scientific research to support future military technologies and capabilities.
  • 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: AIRDO
Triple: [Japanese domestic airport network, servedBy, AIRDO]
Generated description
AIRDO is a Japanese regional airline based in Hokkaido that operates domestic flights connecting Hokkaido with major cities across Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AIRDO
Target entity description: AIRDO is a Japanese regional airline based in Hokkaido that operates domestic flights connecting Hokkaido with major cities across Japan.
  • A. airag
    Airag is a traditional Mongolian fermented mare’s milk drink, mildly alcoholic and sour, commonly consumed during cultural events and daily life on the steppe.
  • B. Airok
    Airok is a small settlement located on Ailinglaplap Atoll in the Marshall Islands.
  • C. AARI
    AARI is a Russian polar research institute that leads and coordinates the country’s scientific activities in the Arctic and Antarctic regions.
  • D. Aari
    Aari is an Omotic language spoken primarily by the Aari people in southwestern Ethiopia.
  • E. ARO
    ARO is the U.S. Army Research Office, a primary Army organization that funds and manages basic scientific research to support future military technologies and capabilities.
  • 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_69c68827b5e481908dc05e145b2c92d4 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea763f208190af1210cd8d2a05c9 completed March 27, 2026, 8:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d39dab6081909842bfa37ff3f972 completed March 28, 2026, 1:11 p.m.
NEDg Description generation batch_69c7d4690adc81909abbfb7a756f453d completed March 28, 2026, 1:15 p.m.
NED2 Entity disambiguation (via description) batch_69c7d517a7108190893878cbef7d1a3a completed March 28, 2026, 1:18 p.m.
Created at: March 27, 2026, 2:56 p.m.