Triple

T22615834
Position Surface form Disambiguated ID Type / Status
Subject municipality of Heusden E558142 entity
Predicate contains P35 FINISHED
Object Haarsteeg
Haarsteeg is a village in the Dutch province of North Brabant, located within the municipality of Heusden.
E1545882 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: Haarsteeg | Statement: [municipality of Heusden, contains, Haarsteeg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haarsteeg
Context triple: [municipality of Heusden, contains, Haarsteeg]
  • A. Haarstrang
    Haarstrang is a low mountain range in North Rhine-Westphalia, Germany, forming a natural boundary between the Soest plain and the higher Sauerland region.
  • B. Haacht
    Haacht is a municipality in the Flemish Brabant province of Belgium, known for its local brewery and semi-rural character near the city of Leuven.
  • C. Haaren
    Haaren is a village and former municipality in the Dutch province of North Brabant.
  • D. Hondsrug
    Hondsrug is a prominent elongated ridge of higher ground in the Dutch provinces of Drenthe and Groningen, known for its glacial origin and distinctive landscape.
  • E. Haasgat
    Haasgat is a fossil-bearing cave site in South Africa known for its valuable paleoanthropological and paleontological remains.
  • 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: Haarsteeg
Triple: [municipality of Heusden, contains, Haarsteeg]
Generated description
Haarsteeg is a village in the Dutch province of North Brabant, located within the municipality of Heusden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haarsteeg
Target entity description: Haarsteeg is a village in the Dutch province of North Brabant, located within the municipality of Heusden.
  • A. Haarstrang
    Haarstrang is a low mountain range in North Rhine-Westphalia, Germany, forming a natural boundary between the Soest plain and the higher Sauerland region.
  • B. Haacht
    Haacht is a municipality in the Flemish Brabant province of Belgium, known for its local brewery and semi-rural character near the city of Leuven.
  • C. Haaren
    Haaren is a village and former municipality in the Dutch province of North Brabant.
  • D. Hondsrug
    Hondsrug is a prominent elongated ridge of higher ground in the Dutch provinces of Drenthe and Groningen, known for its glacial origin and distinctive landscape.
  • E. Haasgat
    Haasgat is a fossil-bearing cave site in South Africa known for its valuable paleoanthropological and paleontological remains.
  • 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_69e24545a8e08190bfa7482a2c725ff1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f167edec2481909c2f06607b3cb8f6 completed April 29, 2026, 2:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b4dff7e008190a16aa3ff4e8e50a8 completed May 18, 2026, 5:35 p.m.
NEDg Description generation batch_6a0b4fe0bbd88190b09e2b131a8920b2 completed May 18, 2026, 5:44 p.m.
NED2 Entity disambiguation (via description) batch_6a0b506216a481908b05ab46ff3e8ce1 completed May 18, 2026, 5:46 p.m.
Created at: April 17, 2026, 2:59 p.m.