Triple

T315919
Position Surface form Disambiguated ID Type / Status
Subject Kutaisi E7705 entity
Predicate hasUNLOCODE P1492 FINISHED
Object GEKUT
GEKUT is the UN/LOCODE identifier for the city of Kutaisi in Georgia, used in international trade and transport logistics.
E40615 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: GEKUT | Statement: [Kutaisi, hasUNLOCODE, GEKUT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GEKUT
Context triple: [Kutaisi, hasUNLOCODE, GEKUT]
  • A. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • B. Gassel
    Gassel is a village in the Dutch province of North Brabant, known historically as a separate municipality before being incorporated into a larger administrative unit.
  • C. Kigensetsu
    Kigensetsu was a pre-World War II Japanese national holiday that celebrated the mythical founding of Japan and the divine origins of the emperor.
  • D. Gelem Gelem
    Gelem Gelem is the Romani people’s anthem, a song that expresses their shared history, suffering, and cultural identity.
  • E. Goettsch
    Goettsch is a surname most prominently associated with the architecture firm Lohan Caprile Goettsch Architects and its architectural practice.
  • 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: GEKUT
Triple: [Kutaisi, hasUNLOCODE, GEKUT]
Generated description
GEKUT is the UN/LOCODE identifier for the city of Kutaisi in Georgia, used in international trade and transport logistics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: GEKUT
Target entity description: GEKUT is the UN/LOCODE identifier for the city of Kutaisi in Georgia, used in international trade and transport logistics.
  • A. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • B. Gassel
    Gassel is a village in the Dutch province of North Brabant, known historically as a separate municipality before being incorporated into a larger administrative unit.
  • C. Kigensetsu
    Kigensetsu was a pre-World War II Japanese national holiday that celebrated the mythical founding of Japan and the divine origins of the emperor.
  • D. Gelem Gelem
    Gelem Gelem is the Romani people’s anthem, a song that expresses their shared history, suffering, and cultural identity.
  • E. Goettsch
    Goettsch is a surname most prominently associated with the architecture firm Lohan Caprile Goettsch Architects and its architectural practice.
  • 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_69a2e7e7af7881908890039d6be4e9b8 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ea6462148190825acc57f6d2adaf completed Feb. 28, 2026, 1:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3c41c00888190861d2b6d4bfc8904 completed March 1, 2026, 4:44 a.m.
NEDg Description generation batch_69a3c5cca244819082e9565558f23dbe completed March 1, 2026, 4:51 a.m.
NED2 Entity disambiguation (via description) batch_69a3c64599ac81908e30e5452cc91b97 completed March 1, 2026, 4:53 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.