Triple

T9977607
Position Surface form Disambiguated ID Type / Status
Subject Pier A E196371 entity
Predicate locatedIn P40 FINISHED
Object Zaventem E192168 NE FINISHED

How this triple was built (2 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: Zaventem | Statement: [Pier A, locatedIn, Zaventem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zaventem
Context triple: [Pier A, locatedIn, Zaventem]
  • A. Zaventem chosen
    Zaventem is a municipality in the Flemish Brabant province of Belgium, best known internationally as the site of Brussels Airport.
  • B. Brussels Airport
    Brussels Airport is the main international airport serving Brussels and one of Belgium’s busiest air transport hubs for passengers and cargo.
  • C. Brussels South Charleroi Airport
    Brussels South Charleroi Airport is a major low-cost international airport in Belgium, widely used by budget airlines and serving as an alternative to Brussels Airport.
  • D. Liège Airport
    Liège Airport is a major international cargo and passenger airport in eastern Belgium, known as one of Europe’s leading freight hubs.
  • E. Antwerp International Airport
    Antwerp International Airport is a small regional airport in Antwerp, Belgium, primarily serving short-haul European flights and general aviation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82eea2b88190a0e511d21a31f386 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb84ef8ac8190abbe78b7611c5309 completed April 2, 2026, 12:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69d26a08a60c81909be30a442787328b completed April 5, 2026, 1:56 p.m.
Created at: March 30, 2026, 8:48 p.m.