Triple

T18003523
Position Surface form Disambiguated ID Type / Status
Subject Coral Harbour E430685 entity
Predicate airportIATAcode P418 FINISHED
Object YZS
YZS is the IATA airport code for Coral Harbour Airport, which serves the community of Coral Harbour in Nunavut, Canada.
E1300320 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: YZS | Statement: [Coral Harbour, airportIATAcode, YZS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: YZS
Context triple: [Coral Harbour, airportIATAcode, YZS]
  • A. YZT
    YZT is the IATA airport code for Port Hardy Airport, which serves the town of Port Hardy on the northern tip of Vancouver Island in British Columbia, Canada.
  • B. YZF
    YZF is the IATA airport code for Yellowknife Airport, the primary air gateway to Yellowknife in Canada’s Northwest Territories.
  • C. Yz
    Yz is a magical thunderbolt-summoning entity from DC Comics that empowers the superhero Johnny Thunder.
  • D. YZZ
    YZZ is the IATA airport code for Trail Regional Airport, a small regional airport serving the Trail area in British Columbia, Canada.
  • E. ZYR
    ZYR is the IATA code for Brussels-South railway station, a major international rail hub in Brussels, Belgium.
  • 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: YZS
Triple: [Coral Harbour, airportIATAcode, YZS]
Generated description
YZS is the IATA airport code for Coral Harbour Airport, which serves the community of Coral Harbour in Nunavut, Canada.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: YZS
Target entity description: YZS is the IATA airport code for Coral Harbour Airport, which serves the community of Coral Harbour in Nunavut, Canada.
  • A. YZT
    YZT is the IATA airport code for Port Hardy Airport, which serves the town of Port Hardy on the northern tip of Vancouver Island in British Columbia, Canada.
  • B. YZF
    YZF is the IATA airport code for Yellowknife Airport, the primary air gateway to Yellowknife in Canada’s Northwest Territories.
  • C. Yz
    Yz is a magical thunderbolt-summoning entity from DC Comics that empowers the superhero Johnny Thunder.
  • D. YZZ
    YZZ is the IATA airport code for Trail Regional Airport, a small regional airport serving the Trail area in British Columbia, Canada.
  • E. ZYR
    ZYR is the IATA code for Brussels-South railway station, a major international rail hub in Brussels, Belgium.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b3ea60608190b977644e946407b7 completed April 19, 2026, 10:52 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0337b6b7e48190a649dda888450b2d completed May 12, 2026, 2:22 p.m.
NEDg Description generation batch_6a033ca755e08190aa5003164b49f196 completed May 12, 2026, 2:43 p.m.
NED2 Entity disambiguation (via description) batch_6a033d7a601c8190a4746adfdfffbca8 completed May 12, 2026, 2:47 p.m.
Created at: April 10, 2026, 10:23 a.m.