Triple

T3758656
Position Surface form Disambiguated ID Type / Status
Subject Tunis Metro E82109 entity
Predicate operator P179 FINISHED
Object Transtu
Transtu is the public transport authority in Tunis responsible for operating the city’s metro and other urban transit services.
 E386961 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: Transtu | Statement: [Tunis Metro, operator, Transtu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Transtu
Context triple: [Tunis Metro, operator, Transtu]
  • A. Transy
    Transy is the commonly used nickname for Transylvania University, a private liberal arts college in Lexington, Kentucky.
  • B. Trasianka
    Trasianka is a mixed East Slavic speech variety, primarily combining elements of Belarusian and Russian, commonly used in informal communication in Belarus.
  • C. Troinex
    Troinex is a small municipality in the canton of Geneva in southwestern Switzerland, situated near the French border.
  • D. Tiel
    Tiel is a historic Dutch city situated along the River Waal, known for its fruit cultivation and role as a regional trade center in the province of Gelderland.
  • E. Trostan
    Trostan is a mountain in Northern Ireland and the highest peak in County Antrim.
  • 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: Transtu
Triple: [Tunis Metro, operator, Transtu]
Generated description
Transtu is the public transport authority in Tunis responsible for operating the city’s metro and other urban transit services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Transtu
Target entity description: Transtu is the public transport authority in Tunis responsible for operating the city’s metro and other urban transit services.
  • A. Transy
    Transy is the commonly used nickname for Transylvania University, a private liberal arts college in Lexington, Kentucky.
  • B. Trasianka
    Trasianka is a mixed East Slavic speech variety, primarily combining elements of Belarusian and Russian, commonly used in informal communication in Belarus.
  • C. Troinex
    Troinex is a small municipality in the canton of Geneva in southwestern Switzerland, situated near the French border.
  • D. Tiel
    Tiel is a historic Dutch city situated along the River Waal, known for its fruit cultivation and role as a regional trade center in the province of Gelderland.
  • E. Trostan
    Trostan is a mountain in Northern Ireland and the highest peak in County Antrim.
  • 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_69ad8b1db40081908b61ffa6b78afd4d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcbc20b20819095fedf803aadc53a completed March 8, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4e5133ba48190a18ea170e3b9e1cd completed March 14, 2026, 4:33 a.m.
NEDg Description generation batch_69b4e62d284881908531b93645649f45 completed March 14, 2026, 4:38 a.m.
NED2 Entity disambiguation (via description) batch_69b4ea2b19e48190864d2114603865ed completed March 14, 2026, 4:55 a.m.
Created at: March 8, 2026, 3:35 p.m.