Triple

T16606246
Position Surface form Disambiguated ID Type / Status
Subject Christo E403453 entity
Predicate notableWork P4 FINISHED
Object Wrapped Cans
Wrapped Cans is an early conceptual artwork by Christo consisting of everyday tin cans encased in fabric or other materials, exemplifying his signature approach to wrapping ordinary objects to transform their perception.
E1223459 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: Wrapped Cans | Statement: [Christo, notableWork, Wrapped Cans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wrapped Cans
Context triple: [Christo, notableWork, Wrapped Cans]
  • A. Pepsi Can
    Pepsi Can is a NASCAR race car paint scheme, notably used on Jeff Gordon’s No. 24 car, featuring bold Pepsi branding and colors that resemble a classic soda can design.
  • B. Wrapped in Plastic
    "Wrapped in Plastic" is a track by the American rock band Marilyn Manson from their debut studio album, "Portrait of an American Family."
  • C. Beercan
    "Beercan" is a song by American musician Beck, known for its offbeat lyrics and genre-blending alternative rock sound.
  • D. Bottle
    Bottle is a lightweight Python web framework used for building simple web applications and APIs in a single file.
  • E. Ultrawrap
    Ultrawrap is an Ontology-Based Data Access (OBDA) system that enables querying relational databases through an ontology-driven, semantic layer.
  • 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: Wrapped Cans
Triple: [Christo, notableWork, Wrapped Cans]
Generated description
Wrapped Cans is an early conceptual artwork by Christo consisting of everyday tin cans encased in fabric or other materials, exemplifying his signature approach to wrapping ordinary objects to transform their perception.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Wrapped Cans
Target entity description: Wrapped Cans is an early conceptual artwork by Christo consisting of everyday tin cans encased in fabric or other materials, exemplifying his signature approach to wrapping ordinary objects to transform their perception.
  • A. Pepsi Can
    Pepsi Can is a NASCAR race car paint scheme, notably used on Jeff Gordon’s No. 24 car, featuring bold Pepsi branding and colors that resemble a classic soda can design.
  • B. Wrapped in Plastic
    "Wrapped in Plastic" is a track by the American rock band Marilyn Manson from their debut studio album, "Portrait of an American Family."
  • C. Beercan
    "Beercan" is a song by American musician Beck, known for its offbeat lyrics and genre-blending alternative rock sound.
  • D. Bottle
    Bottle is a lightweight Python web framework used for building simple web applications and APIs in a single file.
  • E. Ultrawrap
    Ultrawrap is an Ontology-Based Data Access (OBDA) system that enables querying relational databases through an ontology-driven, semantic layer.
  • 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_69d883880d0c81908b5fcd454e767b60 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e36090cf388190b401c55230912104 completed April 18, 2026, 10:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0075a8a6248190a9e2bb469d821c66 completed May 10, 2026, 12:10 p.m.
NEDg Description generation batch_6a007705f57881908b07a20ae8957c64 completed May 10, 2026, 12:16 p.m.
NED2 Entity disambiguation (via description) batch_6a007b18f0b08190a9ddc6ad7358d6b8 completed May 10, 2026, 12:33 p.m.
Created at: April 10, 2026, 5:17 a.m.