Triple

T10117664
Position Surface form Disambiguated ID Type / Status
Subject Belgian Special Operations Forces E223203 entity
Predicate garrison P75 FINISHED
Object Heverlee E573691 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: Heverlee | Statement: [Belgian Special Operations Forces, garrison, Heverlee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heverlee
Context triple: [Belgian Special Operations Forces, garrison, Heverlee]
  • A. Heverlee chosen
    Heverlee is a suburb of Leuven in the Flemish Brabant province of Belgium, known for its residential areas, green spaces, and nearby university facilities.
  • B. La Hulpe
    La Hulpe is a small, affluent municipality in Walloon Brabant, Belgium, known for its green surroundings and the Château de La Hulpe within the Solvay Regional Estate.
  • C. Overpelt
    Overpelt is a town in the Belgian province of Limburg, known for its green surroundings and local waterways.
  • D. Weyts
    Weyts is a Dutch-language surname of Belgian origin, notably borne by Flemish politician Ben Weyts.
  • E. Berghem
    Berghem is a village in the Dutch province of North Brabant that is now administratively part of the municipality of Oss.
  • 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_69ca8422047c81909d66b717b8b18cf3 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd26317948190901197adbac01ed3 completed April 2, 2026, 2:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc350310819096cca4cc251e3428 completed April 5, 2026, 8:55 p.m.
Created at: March 30, 2026, 9:04 p.m.