Triple

T13312106
Position Surface form Disambiguated ID Type / Status
Subject Bulgari E317092 entity
Predicate notableCollection P22 FINISHED
Object Serpenti
Serpenti is Bulgari’s iconic snake-inspired jewelry and watch collection, renowned for its coiling designs and luxurious, glamorous aesthetic.
E1032866 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: Serpenti | Statement: [Bulgari, notableCollection, Serpenti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Serpenti
Context triple: [Bulgari, notableCollection, Serpenti]
  • A. Serpentes
    Serpentes is the suborder of legless, elongated reptiles commonly known as snakes, encompassing a diverse group of carnivorous species found worldwide.
  • B. Schlangen
    Schlangen is a small municipality in the Lippe district of North Rhine-Westphalia, Germany, known for its rural character and proximity to the Teutoburg Forest.
  • C. Serpent
    Serpent is a symmetric block cipher designed as a highly secure, conservative candidate for the Advanced Encryption Standard (AES) competition.
  • D. Slither
    Slither is a 2006 horror-comedy film that blends grotesque alien invasion elements with dark humor and cult-movie sensibilities.
  • E. Slither
    Slither is a 1973 American crime-comedy film known for its offbeat humor and ensemble cast, including Louise Lasser and James Caan.
  • 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: Serpenti
Triple: [Bulgari, notableCollection, Serpenti]
Generated description
Serpenti is Bulgari’s iconic snake-inspired jewelry and watch collection, renowned for its coiling designs and luxurious, glamorous aesthetic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Serpenti
Target entity description: Serpenti is Bulgari’s iconic snake-inspired jewelry and watch collection, renowned for its coiling designs and luxurious, glamorous aesthetic.
  • A. Serpentes
    Serpentes is the suborder of legless, elongated reptiles commonly known as snakes, encompassing a diverse group of carnivorous species found worldwide.
  • B. Schlangen
    Schlangen is a small municipality in the Lippe district of North Rhine-Westphalia, Germany, known for its rural character and proximity to the Teutoburg Forest.
  • C. Serpent
    Serpent is a symmetric block cipher designed as a highly secure, conservative candidate for the Advanced Encryption Standard (AES) competition.
  • D. Slither
    Slither is a 2006 horror-comedy film that blends grotesque alien invasion elements with dark humor and cult-movie sensibilities.
  • E. Slither
    Slither is a 1973 American crime-comedy film known for its offbeat humor and ensemble cast, including Louise Lasser and James Caan.
  • 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_69d806b40ab4819094adf6c374f4811a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990f6d34c8190ba19dc2df7d42c22 completed April 11, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716e7b9a48190a33b04df8ad45ed8 completed May 3, 2026, 9:35 a.m.
NEDg Description generation batch_69f717b868608190971c38f26b61cf28 completed May 3, 2026, 9:39 a.m.
NED2 Entity disambiguation (via description) batch_69f718705a44819084b97d35a10ee50d completed May 3, 2026, 9:42 a.m.
Created at: April 9, 2026, 9:29 p.m.