Triple

T5807377
Position Surface form Disambiguated ID Type / Status
Subject Flemish Brabant E128778 entity
Predicate contains P35 FINISHED
Object Halle
Halle is a historic city in the Belgian province of Flemish Brabant, known for its medieval architecture and the Basilica of Saint Martin, a notable pilgrimage site.
 E547478 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: Halle | Statement: [Flemish Brabant, contains, Halle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Halle
Context triple: [Flemish Brabant, contains, Halle]
  • A. Halle
    Halle is a surname most notably borne by Morris Halle, a prominent linguist and phonologist.
  • B. Halle (Saale)
    Halle (Saale) is a major city in the German state of Saxony-Anhalt, known as an important economic, cultural, and educational center, including being home to the Martin Luther University of Halle-Wittenberg.
  • C. Blentheim
    Blentheim is a location in New Zealand that serves as one of the seats of the High Court of New Zealand.
  • D. Hallen
    Hallen is a small village in South Gloucestershire, England, situated near Bristol and known for its rural character and proximity to major transport routes.
  • E. Hanover
    Hanover is a small New Hampshire town best known as the home of Dartmouth College, an Ivy League institution.
  • 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: Halle
Triple: [Flemish Brabant, contains, Halle]
Generated description
Halle is a historic city in the Belgian province of Flemish Brabant, known for its medieval architecture and the Basilica of Saint Martin, a notable pilgrimage site.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Halle
Target entity description: Halle is a historic city in the Belgian province of Flemish Brabant, known for its medieval architecture and the Basilica of Saint Martin, a notable pilgrimage site.
  • A. Halle
    Halle is a surname most notably borne by Morris Halle, a prominent linguist and phonologist.
  • B. Halle (Saale)
    Halle (Saale) is a major city in the German state of Saxony-Anhalt, known as an important economic, cultural, and educational center, including being home to the Martin Luther University of Halle-Wittenberg.
  • C. Blentheim
    Blentheim is a location in New Zealand that serves as one of the seats of the High Court of New Zealand.
  • D. Hallen
    Hallen is a small village in South Gloucestershire, England, situated near Bristol and known for its rural character and proximity to major transport routes.
  • E. Hanover
    Hanover is a small New Hampshire town best known as the home of Dartmouth College, an Ivy League institution.
  • 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_69c0084788848190bcf71f6bc5d71597 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02b17417081908779741b9bfbb720 completed March 22, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0983ded9c8190b37372627c1e3a50 completed March 23, 2026, 1:32 a.m.
NEDg Description generation batch_69c0990bf38081908c09c5dfe660c35b completed March 23, 2026, 1:36 a.m.
NED2 Entity disambiguation (via description) batch_69c099bd26fc8190a58bf483a6d4cbca completed March 23, 2026, 1:39 a.m.
Created at: March 22, 2026, 3:52 p.m.