Triple

T10334226
Position Surface form Disambiguated ID Type / Status
Subject Hyacinth E242957 entity
Predicate hasVariant P455 FINISHED
Object Jacinthe
Jacinthe is a variant form of the name Hyacinth, often associated with the fragrant spring flower and its rich, jewel-like colors.
 E856612 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: Jacinthe | Statement: [Hyacinth, hasVariant, Jacinthe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jacinthe
Context triple: [Hyacinth, hasVariant, Jacinthe]
  • A. Groseau
    Groseau is a smaller watercourse in southeastern France that serves as a tributary feeding into the Ouvèze River.
  • B. Sambreville
    Sambreville is a municipality in the Walloon region of Belgium, situated along the Sambre River and known for its industrial and mining heritage.
  • C. Hélécine
    Hélécine is a small rural municipality in the province of Walloon Brabant in Wallonia, Belgium.
  • D. Valée
    Valée is a French surname most notably borne by Sylvain Charles Valée, a 19th-century French military officer and Marshal of France.
  • E. Tiphaine
    Tiphaine is a French given name, notably borne by Tiphaine Auzière, the daughter of Brigitte Macron.
  • 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: Jacinthe
Triple: [Hyacinth, hasVariant, Jacinthe]
Generated description
Jacinthe is a variant form of the name Hyacinth, often associated with the fragrant spring flower and its rich, jewel-like colors.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jacinthe
Target entity description: Jacinthe is a variant form of the name Hyacinth, often associated with the fragrant spring flower and its rich, jewel-like colors.
  • A. Groseau
    Groseau is a smaller watercourse in southeastern France that serves as a tributary feeding into the Ouvèze River.
  • B. Sambreville
    Sambreville is a municipality in the Walloon region of Belgium, situated along the Sambre River and known for its industrial and mining heritage.
  • C. Hélécine
    Hélécine is a small rural municipality in the province of Walloon Brabant in Wallonia, Belgium.
  • D. Valée
    Valée is a French surname most notably borne by Sylvain Charles Valée, a 19th-century French military officer and Marshal of France.
  • E. Tiphaine
    Tiphaine is a French given name, notably borne by Tiphaine Auzière, the daughter of Brigitte Macron.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4dfc366b481909c49f199892e9d42 completed April 7, 2026, 10:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69d75054515081908240f985f8b6e2df completed April 9, 2026, 7:08 a.m.
NEDg Description generation batch_69d75184cd1c81909e86153bbb516d4f completed April 9, 2026, 7:13 a.m.
NED2 Entity disambiguation (via description) batch_69d7521f0d1c81909f9ae3b46981cdbc completed April 9, 2026, 7:15 a.m.
Created at: April 6, 2026, 11:53 a.m.