Triple

T18754996
Position Surface form Disambiguated ID Type / Status
Subject Amber E458626 entity
Predicate hasVariantSpelling P457 FINISHED
Object Ambre
Ambre is an alternative French-influenced spelling of "Amber," commonly used as a given name and in references to the fossilized tree resin.
 E1341206 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: Ambre | Statement: [Amber, hasVariantSpelling, Ambre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ambre
Context triple: [Amber, hasVariantSpelling, Ambre]
  • A. Camay
    Camay is a track featured on the album "Ironman" by rapper Ghostface Killah.
  • B. Lemonum
    Lemonum was an important ancient Roman town in Gaul, located at the site of modern-day Poitiers in western France.
  • C. Jasmin
    Jasmin is a Paris Métro station in the 16th arrondissement, named after the 19th-century French poet Jasmin.
  • D. Maurane
    Maurane was a Belgian singer and songwriter renowned for her rich, warm voice and emotive performances in French-language pop and chanson.
  • E. Tramelan
    Tramelan is a municipality in the French-speaking Bernese Jura region of Switzerland, known for its watchmaking industry and scenic Jura landscapes.
  • 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: Ambre
Triple: [Amber, hasVariantSpelling, Ambre]
Generated description
Ambre is an alternative French-influenced spelling of "Amber," commonly used as a given name and in references to the fossilized tree resin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ambre
Target entity description: Ambre is an alternative French-influenced spelling of "Amber," commonly used as a given name and in references to the fossilized tree resin.
  • A. Camay
    Camay is a track featured on the album "Ironman" by rapper Ghostface Killah.
  • B. Lemonum
    Lemonum was an important ancient Roman town in Gaul, located at the site of modern-day Poitiers in western France.
  • C. Jasmin
    Jasmin is a Paris Métro station in the 16th arrondissement, named after the 19th-century French poet Jasmin.
  • D. Maurane
    Maurane was a Belgian singer and songwriter renowned for her rich, warm voice and emotive performances in French-language pop and chanson.
  • E. Tramelan
    Tramelan is a municipality in the French-speaking Bernese Jura region of Switzerland, known for its watchmaking industry and scenic Jura landscapes.
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e579f084208190a4b3563d47154e69 completed April 20, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a053d3967408190bd9fc7493179a198 completed May 14, 2026, 3:10 a.m.
NEDg Description generation batch_6a053eee3d4c81909706ea5e19aef1cf completed May 14, 2026, 3:18 a.m.
NED2 Entity disambiguation (via description) batch_6a053fa12df48190b1a8bbdd5f3080a3 completed May 14, 2026, 3:21 a.m.
Created at: April 10, 2026, 11:51 a.m.