Triple

T8679483
Position Surface form Disambiguated ID Type / Status
Subject Howel E205998 entity
Predicate hasVariant P455 FINISHED
Object Hoel
Hoel is a given name and surname of Breton and Welsh origin, historically borne by several medieval rulers and later used in various European cultures.
 E752111 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: Hoel | Statement: [Howel, hasVariant, Hoel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hoel
Context triple: [Howel, hasVariant, Hoel]
  • A. Hoelun
    Hoelun was a Mongol noblewoman best known as the mother of Genghis Khan and a key matriarchal figure in the early Mongol Empire.
  • B. Hille
    Hille is a surname and place name that appears as a variant form of "Hill" in certain linguistic or regional contexts.
  • C. Bickel
    Bickel is the family name of the American actor Fredric March, a prominent star of classic Hollywood cinema.
  • D. Helleren
    Helleren is a small historic settlement in Norway known for its traditional houses built under a large rock overhang near the Jøssingfjord.
  • E. Hellerud
    Hellerud is a residential neighborhood in Oslo, Norway, known for its hillside location and proximity to green areas and public transport.
  • 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: Hoel
Triple: [Howel, hasVariant, Hoel]
Generated description
Hoel is a given name and surname of Breton and Welsh origin, historically borne by several medieval rulers and later used in various European cultures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hoel
Target entity description: Hoel is a given name and surname of Breton and Welsh origin, historically borne by several medieval rulers and later used in various European cultures.
  • A. Hoelun
    Hoelun was a Mongol noblewoman best known as the mother of Genghis Khan and a key matriarchal figure in the early Mongol Empire.
  • B. Hille
    Hille is a surname and place name that appears as a variant form of "Hill" in certain linguistic or regional contexts.
  • C. Bickel
    Bickel is the family name of the American actor Fredric March, a prominent star of classic Hollywood cinema.
  • D. Helleren
    Helleren is a small historic settlement in Norway known for its traditional houses built under a large rock overhang near the Jøssingfjord.
  • E. Hellerud
    Hellerud is a residential neighborhood in Oslo, Norway, known for its hillside location and proximity to green areas and public transport.
  • 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_69ca835379688190aa06b9d98e684d58 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc49f8fa948190a070e90d17b4ede2 completed March 31, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef3b2be2081908a8744b77c4753f2 completed April 2, 2026, 10:54 p.m.
NEDg Description generation batch_69cef52000048190bc5451cfb6446ced completed April 2, 2026, 11 p.m.
NED2 Entity disambiguation (via description) batch_69cef809df548190b4f9ecc709b3b065 completed April 2, 2026, 11:13 p.m.
Created at: March 30, 2026, 6:32 p.m.