Triple

T4904153
Position Surface form Disambiguated ID Type / Status
Subject Tbilisi Metro E109873 entity
Predicate hasStation P35 FINISHED
Object Delisi
Delisi is a metro station in Tbilisi, Georgia, serving as one of the stops on the city’s rapid transit network.
 E478960 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: Delisi | Statement: [Tbilisi Metro, hasStation, Delisi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Delisi
Context triple: [Tbilisi Metro, hasStation, Delisi]
  • A. Fensalir
    Fensalir is the misty, marsh-surrounded hall in Norse mythology that serves as the home of the goddess Frigg.
  • B. Visperad
    Visperad is a Zoroastrian liturgical text and ceremony that expands upon the Yasna ritual with additional invocations to various divine beings.
  • C. Chéserex
    Chéserex is a small Swiss municipality in the canton of Vaud, situated near the Jura Mountains above Lake Geneva.
  • D. Reitia
    Reitia is an ancient goddess venerated by the Veneti people of northeastern Italy, often linked to writing, healing, and protection.
  • E. Plegridy
    Plegridy is a pegylated interferon beta-1a medication used to treat relapsing forms of multiple sclerosis.
  • 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: Delisi
Triple: [Tbilisi Metro, hasStation, Delisi]
Generated description
Delisi is a metro station in Tbilisi, Georgia, serving as one of the stops on the city’s rapid transit network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Delisi
Target entity description: Delisi is a metro station in Tbilisi, Georgia, serving as one of the stops on the city’s rapid transit network.
  • A. Fensalir
    Fensalir is the misty, marsh-surrounded hall in Norse mythology that serves as the home of the goddess Frigg.
  • B. Visperad
    Visperad is a Zoroastrian liturgical text and ceremony that expands upon the Yasna ritual with additional invocations to various divine beings.
  • C. Chéserex
    Chéserex is a small Swiss municipality in the canton of Vaud, situated near the Jura Mountains above Lake Geneva.
  • D. Reitia
    Reitia is an ancient goddess venerated by the Veneti people of northeastern Italy, often linked to writing, healing, and protection.
  • E. Plegridy
    Plegridy is a pegylated interferon beta-1a medication used to treat relapsing forms of multiple sclerosis.
  • 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_69bd441180708190ba42ffb44fea533a completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6e6fdeac81909092f51ae40ad20e completed March 20, 2026, 3:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69be6fdaaf588190a180d0bf5979c2d2 completed March 21, 2026, 10:15 a.m.
NEDg Description generation batch_69be70b15c508190bcd723862b8e9633 completed March 21, 2026, 10:19 a.m.
NED2 Entity disambiguation (via description) batch_69be7139a288819087598a7da8c6ad42 completed March 21, 2026, 10:21 a.m.
Created at: March 20, 2026, 1:29 p.m.