Triple

T6645309
Position Surface form Disambiguated ID Type / Status
Subject Thiers arrondissement E150684 entity
Predicate contains P35 FINISHED
Object Bulhon
Bulhon is a small commune in central France’s Puy-de-Dôme department, situated within the Thiers arrondissement.
E610478 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: Bulhon | Statement: [Thiers arrondissement, contains, Bulhon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bulhon
Context triple: [Thiers arrondissement, contains, Bulhon]
  • A. Balgüe
    Balgüe is a small rural village on Ometepe Island in Lake Nicaragua, known for its scenic setting near volcanic landscapes and eco-tourism lodges.
  • B. Gulgong
    Gulgong is a historic gold rush town in New South Wales, Australia, known for its well-preserved 19th-century streetscapes and heritage buildings.
  • C. Buk-gu
    Buk-gu is a northern administrative district of the metropolitan city of Ulsan in South Korea.
  • D. Bomunsan
    Bomunsan is a prominent mountain and recreational area in Daejeon, South Korea, known for its hiking trails, temples, and city views.
  • E. Kohunlich
    Kohunlich is a large Maya archaeological site in southern Quintana Roo, Mexico, noted for its monumental architecture and well-preserved stucco masks.
  • 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: Bulhon
Triple: [Thiers arrondissement, contains, Bulhon]
Generated description
Bulhon is a small commune in central France’s Puy-de-Dôme department, situated within the Thiers arrondissement.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bulhon
Target entity description: Bulhon is a small commune in central France’s Puy-de-Dôme department, situated within the Thiers arrondissement.
  • A. Balgüe
    Balgüe is a small rural village on Ometepe Island in Lake Nicaragua, known for its scenic setting near volcanic landscapes and eco-tourism lodges.
  • B. Gulgong
    Gulgong is a historic gold rush town in New South Wales, Australia, known for its well-preserved 19th-century streetscapes and heritage buildings.
  • C. Buk-gu
    Buk-gu is a northern administrative district of the metropolitan city of Ulsan in South Korea.
  • D. Bomunsan
    Bomunsan is a prominent mountain and recreational area in Daejeon, South Korea, known for its hiking trails, temples, and city views.
  • E. Kohunlich
    Kohunlich is a large Maya archaeological site in southern Quintana Roo, Mexico, noted for its monumental architecture and well-preserved stucco masks.
  • 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_69c687f1a3048190828b7342f7125d5c completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b01bb290819089c4ff2bd2b5e09b completed March 27, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6eef48b488190ac08dc37d4a5d514 completed March 27, 2026, 8:56 p.m.
NEDg Description generation batch_69c6f127d9188190849959aaae10f769 completed March 27, 2026, 9:05 p.m.
NED2 Entity disambiguation (via description) batch_69c6f5318764819092eca02a5f300e2a completed March 27, 2026, 9:22 p.m.
Created at: March 27, 2026, 2 p.m.