Triple

T16847361
Position Surface form Disambiguated ID Type / Status
Subject Gisborne Airport E409578 entity
Predicate IATAcode P418 FINISHED
Object GIS
GIS is the IATA airport code for Gisborne Airport in Gisborne, New Zealand.
 E1236135 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: GIS | Statement: [Gisborne Airport, IATAcode, GIS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GIS
Context triple: [Gisborne Airport, IATAcode, GIS]
  • A. GIS
    The Egyptian General Intelligence Service (GIS) is Egypt’s primary intelligence agency responsible for foreign intelligence gathering, national security, and covert operations.
  • B. GIS
    GIS (Gruppo di Intervento Speciale) is an elite special operations unit of the Italian Carabinieri focused on counter-terrorism, hostage rescue, and high-risk law enforcement missions.
  • C. GIS
    GIS is the Ghana Immigration Service, the government agency responsible for regulating immigration, emigration, and related border control activities in Ghana.
  • D. GIS
    GIS is the station code for Glen Innes railway station in New South Wales, Australia.
  • E. Geographic Information Systems (GIS)
    Geographic Information Systems (GIS) are computer-based tools and methods for capturing, storing, analyzing, and visualizing spatial and geographic data to support mapping and decision-making.
  • 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: GIS
Triple: [Gisborne Airport, IATAcode, GIS]
Generated description
GIS is the IATA airport code for Gisborne Airport in Gisborne, New Zealand.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GIS
Target entity description: GIS is the IATA airport code for Gisborne Airport in Gisborne, New Zealand.
  • A. GIS
    The Egyptian General Intelligence Service (GIS) is Egypt’s primary intelligence agency responsible for foreign intelligence gathering, national security, and covert operations.
  • B. GIS
    GIS (Gruppo di Intervento Speciale) is an elite special operations unit of the Italian Carabinieri focused on counter-terrorism, hostage rescue, and high-risk law enforcement missions.
  • C. GIS
    GIS is the Ghana Immigration Service, the government agency responsible for regulating immigration, emigration, and related border control activities in Ghana.
  • D. GIS
    GIS is the station code for Glen Innes railway station in New South Wales, Australia.
  • E. Geographic Information Systems (GIS)
    Geographic Information Systems (GIS) are computer-based tools and methods for capturing, storing, analyzing, and visualizing spatial and geographic data to support mapping and decision-making.
  • 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_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b354eaf081908fe6f84a330d7866 completed April 18, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb1d555c8190883c82e562b7bfe9 completed May 10, 2026, 5:06 p.m.
NEDg Description generation batch_6a00bbb628208190b0be62a333e7e442 completed May 10, 2026, 5:09 p.m.
NED2 Entity disambiguation (via description) batch_6a00bc3a4b888190bd190b9330e2777d completed May 10, 2026, 5:11 p.m.
Created at: April 10, 2026, 5:24 a.m.