Triple

T21603384
Position Surface form Disambiguated ID Type / Status
Subject Uvea E533106 entity
Predicate airportIATA P418 FINISHED
Object WLS
WLS is the IATA airport code for Hihifo Airport, which serves the island of Wallis in the French overseas collectivity of Wallis and Futuna in the South Pacific.
E1493183 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: WLS | Statement: [Uvea, airportIATA, WLS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WLS
Context triple: [Uvea, airportIATA, WLS]
  • A. WLS
    WLS is a theological seminary in Mequon, Wisconsin, that trains pastors for the Wisconsin Evangelical Lutheran Synod.
  • B. WLS
    WLS is the National Rail station code for Woolston railway station in Southampton, England.
  • C. WLS-FM
    WLS-FM is a Chicago-based commercial radio station known for its classic hits format and shared heritage with the historic WLS brand.
  • D. WLS-TV
    WLS-TV is a major ABC-owned and operated television station serving the Chicago, Illinois media market.
  • E. WLS (AM)
    WLS (AM) is a historic Chicago-based AM radio station known for its influential role in American broadcasting, particularly in music and talk radio.
  • 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: WLS
Triple: [Uvea, airportIATA, WLS]
Generated description
WLS is the IATA airport code for Hihifo Airport, which serves the island of Wallis in the French overseas collectivity of Wallis and Futuna in the South Pacific.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: WLS
Target entity description: WLS is the IATA airport code for Hihifo Airport, which serves the island of Wallis in the French overseas collectivity of Wallis and Futuna in the South Pacific.
  • A. WLS
    WLS is a theological seminary in Mequon, Wisconsin, that trains pastors for the Wisconsin Evangelical Lutheran Synod.
  • B. WLS
    WLS is the National Rail station code for Woolston railway station in Southampton, England.
  • C. WLS-FM
    WLS-FM is a Chicago-based commercial radio station known for its classic hits format and shared heritage with the historic WLS brand.
  • D. WLS-TV
    WLS-TV is a major ABC-owned and operated television station serving the Chicago, Illinois media market.
  • E. WLS (AM)
    WLS (AM) is a historic Chicago-based AM radio station known for its influential role in American broadcasting, particularly in music and talk radio.
  • 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_69e0c46364608190a337dc8720dc2a35 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef17e31c80819090fdd63b5c103acb completed April 27, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09fd366bdc819091d0c0c2e5a179d2 completed May 17, 2026, 5:39 p.m.
NEDg Description generation batch_6a09fe51add4819099fc844931839dea completed May 17, 2026, 5:43 p.m.
NED2 Entity disambiguation (via description) batch_6a09fef4abe48190b6eac6d14aadd110 completed May 17, 2026, 5:46 p.m.
Created at: April 16, 2026, 6:33 p.m.