Triple

T7227432
Position Surface form Disambiguated ID Type / Status
Subject JOG E154815 entity
Predicate formerIcaoCode P18649 FINISHED
Object WIJJ
WIJJ was the former ICAO airport code assigned to JOG, the airport serving Yogyakarta, Indonesia.
E650143 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: WIJJ | Statement: [JOG, formerIcaoCode, WIJJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WIJJ
Context triple: [JOG, formerIcaoCode, WIJJ]
  • A. WIII
    WIII is the ICAO airport code for Soekarno–Hatta International Airport, the main international gateway serving Jakarta, Indonesia.
  • B. WJZ-FM
    WJZ-FM is a Baltimore-based commercial radio station known for its sports and talk programming.
  • C. WMMR
    WMMR is a long-running rock radio station based in Philadelphia, Pennsylvania, known for its influential role in album-oriented rock and local music culture.
  • D. WIQ
    WIQ is the National Rail station code for West India Quay Docklands Light Railway station in London.
  • E. WWHR-FM
    WWHR-FM is the student-run campus radio station of Western Kentucky University, broadcasting a variety of music and programming to the university community and surrounding area.
  • 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: WIJJ
Triple: [JOG, formerIcaoCode, WIJJ]
Generated description
WIJJ was the former ICAO airport code assigned to JOG, the airport serving Yogyakarta, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: WIJJ
Target entity description: WIJJ was the former ICAO airport code assigned to JOG, the airport serving Yogyakarta, Indonesia.
  • A. WIII
    WIII is the ICAO airport code for Soekarno–Hatta International Airport, the main international gateway serving Jakarta, Indonesia.
  • B. WJZ-FM
    WJZ-FM is a Baltimore-based commercial radio station known for its sports and talk programming.
  • C. WMMR
    WMMR is a long-running rock radio station based in Philadelphia, Pennsylvania, known for its influential role in album-oriented rock and local music culture.
  • D. WIQ
    WIQ is the National Rail station code for West India Quay Docklands Light Railway station in London.
  • E. WWHR-FM
    WWHR-FM is the student-run campus radio station of Western Kentucky University, broadcasting a variety of music and programming to the university community and surrounding area.
  • 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_69c68811dd1c8190ac460bb39e64e1f0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6e9df72cc81908d1c04e6e310fbb4 completed March 27, 2026, 8:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7cc17a3788190842a852fb4b96185 completed March 28, 2026, 12:39 p.m.
NEDg Description generation batch_69c7cccdde308190a02c6892f61025e2 completed March 28, 2026, 12:42 p.m.
NED2 Entity disambiguation (via description) batch_69c7cd7e891c8190a6a82227addac434 completed March 28, 2026, 12:45 p.m.
Created at: March 27, 2026, 2:54 p.m.