Triple

T16433949
Position Surface form Disambiguated ID Type / Status
Subject 3XN E399135 entity
Predicate hasSubsidiary P254 FINISHED
Object GXN Innovation
GXN Innovation is a research and innovation arm of the Danish architecture firm 3XN, focusing on sustainable design, circular construction, and advanced material technologies.
E1213461 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: GXN Innovation | Statement: [3XN, hasSubsidiary, GXN Innovation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GXN Innovation
Context triple: [3XN, hasSubsidiary, GXN Innovation]
  • A. Innoventions
    Innoventions was an interactive exhibit pavilion at Epcot in Walt Disney World that showcased emerging technologies and hands-on science displays.
  • B. G2X
    G2X is a compact sports car model produced by Daewoo (also known as the Daewoo G2X), recognized for its sleek design and performance-oriented features.
  • C. Granox Company
    Granox Company is a film production company known for producing the movie "Father Goose."
  • D. Nova Innovation
    Nova Innovation is a renewable energy company specializing in the design, manufacture, and deployment of tidal energy turbines and projects.
  • E. Soon-Tek
    Soon-Tek is the given name of Soon-Tek Oh, a Korean-American actor known for his roles in film, television, and voice acting.
  • 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: GXN Innovation
Triple: [3XN, hasSubsidiary, GXN Innovation]
Generated description
GXN Innovation is a research and innovation arm of the Danish architecture firm 3XN, focusing on sustainable design, circular construction, and advanced material technologies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: GXN Innovation
Target entity description: GXN Innovation is a research and innovation arm of the Danish architecture firm 3XN, focusing on sustainable design, circular construction, and advanced material technologies.
  • A. Innoventions
    Innoventions was an interactive exhibit pavilion at Epcot in Walt Disney World that showcased emerging technologies and hands-on science displays.
  • B. G2X
    G2X is a compact sports car model produced by Daewoo (also known as the Daewoo G2X), recognized for its sleek design and performance-oriented features.
  • C. Granox Company
    Granox Company is a film production company known for producing the movie "Father Goose."
  • D. Nova Innovation
    Nova Innovation is a renewable energy company specializing in the design, manufacture, and deployment of tidal energy turbines and projects.
  • E. Soon-Tek
    Soon-Tek is the given name of Soon-Tek Oh, a Korean-American actor known for his roles in film, television, and voice acting.
  • 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_69d87f2b9024819085c20e52de95d583 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba01a1c8190b5a4700e2364ae63 completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0045872a688190bcab27c6a2b952cd completed May 10, 2026, 8:44 a.m.
NEDg Description generation batch_6a00464f264081908faef31ef15f378a completed May 10, 2026, 8:48 a.m.
NED2 Entity disambiguation (via description) batch_6a004767d1c88190814e83f09383e874 completed May 10, 2026, 8:52 a.m.
Created at: April 10, 2026, 5:10 a.m.