Triple

T5606997
Position Surface form Disambiguated ID Type / Status
Subject Roger & Gallet E147257 entity
Predicate hasProductLine P3585 FINISHED
Object Bois d’Orange
Bois d’Orange is a citrus-inspired fragrance line by Roger & Gallet known for its fresh, orange-blossom and woody notes.
E536932 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: Bois d’Orange | Statement: [Roger & Gallet, hasProductLine, Bois d’Orange]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bois d’Orange
Context triple: [Roger & Gallet, hasProductLine, Bois d’Orange]
  • A. Lignum vitae
    Lignum vitae is a dense, extremely hard tropical hardwood tree native to the Caribbean, renowned for its durable wood and medicinal resin.
  • B. Tanne
    Tanne is a small village in the Harz region of central Germany, now part of the town of Oberharz am Brocken.
  • C. Sakao
    Sakao is an Oceanic language spoken on the island of Espiritu Santo in Vanuatu, noted for its complex phonology and distinctive sound changes.
  • D. Palme
    Palme is a Swedish surname most famously associated with Olof Palme, the former Prime Minister of Sweden and prominent Social Democratic politician.
  • E. Algarrobo
    Algarrobo is a coastal resort town in central Chile known for its beaches and large vacation developments along the Pacific Ocean.
  • 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: Bois d’Orange
Triple: [Roger & Gallet, hasProductLine, Bois d’Orange]
Generated description
Bois d’Orange is a citrus-inspired fragrance line by Roger & Gallet known for its fresh, orange-blossom and woody notes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bois d’Orange
Target entity description: Bois d’Orange is a citrus-inspired fragrance line by Roger & Gallet known for its fresh, orange-blossom and woody notes.
  • A. Lignum vitae
    Lignum vitae is a dense, extremely hard tropical hardwood tree native to the Caribbean, renowned for its durable wood and medicinal resin.
  • B. Tanne
    Tanne is a small village in the Harz region of central Germany, now part of the town of Oberharz am Brocken.
  • C. Sakao
    Sakao is an Oceanic language spoken on the island of Espiritu Santo in Vanuatu, noted for its complex phonology and distinctive sound changes.
  • D. Palme
    Palme is a Swedish surname most famously associated with Olof Palme, the former Prime Minister of Sweden and prominent Social Democratic politician.
  • E. Algarrobo
    Algarrobo is a coastal resort town in central Chile known for its beaches and large vacation developments along the Pacific Ocean.
  • 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_69c0090500f881908374285baf0ac46f completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020fbb8748190841e5e09db3feef1 completed March 22, 2026, 5:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04d4465388190b28f47f11e133b6a completed March 22, 2026, 8:12 p.m.
NEDg Description generation batch_69c04e88680c8190845723f52c060fb7 completed March 22, 2026, 8:18 p.m.
NED2 Entity disambiguation (via description) batch_69c04f7b889c81909db7cb4baf40ed80 completed March 22, 2026, 8:22 p.m.
Created at: March 22, 2026, 3:39 p.m.