Triple

T30423012
Position Surface form Disambiguated ID Type / Status
Subject Georgian culture E773947 entity
Predicate architectureRegion P64798 FINISHED
Object Svaneti towers
Svaneti towers are medieval stone defensive tower-houses in the Svaneti region of northwestern Georgia, renowned for their distinctive multi-story design and role in protecting local communities.
 E1914837 NE FINISHED

How this triple was built (3 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: Svaneti towers | Statement: [Georgian culture, architectureRegion, Svaneti towers]
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: Svaneti towers
Triple: [Georgian culture, architectureRegion, Svaneti towers]
Generated description
Svaneti towers are medieval stone defensive tower-houses in the Svaneti region of northwestern Georgia, renowned for their distinctive multi-story design and role in protecting local communities.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: architectureRegion
Context triple: [Georgian culture, architectureRegion, Svaneti towers]
  • A. regionOfCity
    Indicates that a specified area or district is a constituent part or subdivision of a particular city.
  • B. arealRegion
    Indicates that something occupies or pertains to a specific two-dimensional geographic or spatial area.
  • C. placeRegion chosen
    Indicates that a place is located within, or is part of, a larger geographic or administrative region.
  • D. region1
    Indicates that one entity is the first or primary region associated with, containing, or encompassing another entity.
  • E. regionType
    Indicates the classification or category of a region, specifying what kind of region it is (e.g., administrative, geographic, or functional).
  • F. None of above.

Provenance (6 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_69f22491ba248190b9a4776ca8e42d02 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f7516d5b4081908588a6feb541f355 completed May 3, 2026, 1:45 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2798b34b1c8190a4a238c5f3a250d1 completed June 9, 2026, 4:38 a.m.
NEDg Description generation batch_6a2799c7c1f8819082c3c849d2647821 completed June 9, 2026, 4:42 a.m.
NED2 Entity disambiguation (via description) batch_6a279a7fdfc88190b9aa18cd3b147f7e completed June 9, 2026, 4:45 a.m.
PD Predicate disambiguation batch_69f74d40ebb081909daf60623e38f41d completed May 3, 2026, 1:27 p.m.
Created at: April 29, 2026, 8:06 p.m.