Triple

T15592502
Position Surface form Disambiguated ID Type / Status
Subject Tabuk E374779 entity
Predicate roadDistanceTo P7750 FINISHED
Object Medina
Medina is a major city in western Saudi Arabia revered as Islam’s second holiest site and home to the Prophet Muhammad’s mosque and tomb.
E28127 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: Medina | Statement: [Tabuk, roadDistanceTo, Medina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Medina
Context triple: [Tabuk, roadDistanceTo, Medina]
  • A. Medina
    Medina is a small suburban city in Minnesota known for its rural character, parks, and proximity to the Minneapolis–Saint Paul metropolitan area.
  • B. Medina
    Medina is a common Spanish-origin surname found across the Spanish-speaking world and among their diasporas.
  • C. Medina
    Medina was a Spanish women's magazine associated with the Franco-era Sección Femenina that promoted traditional gender roles and nationalist ideology.
  • D. Medina
    Medina is a municipality in the Cundinamarca Department of Colombia, known for its rural landscapes and location within the Alto Guavio region.
  • E. Medina
    Medina is a coastal municipality in the Philippines known for its scenic shoreline along Macajalar Bay and its largely rural, agriculture-based communities.
  • 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: Medina
Triple: [Tabuk, roadDistanceTo, Medina]
Generated description
Medina is a major city in western Saudi Arabia revered as Islam’s second holiest site and home to the Prophet Muhammad’s mosque and tomb.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Medina
Target entity description: Medina is a major city in western Saudi Arabia revered as Islam’s second holiest site and home to the Prophet Muhammad’s mosque and tomb.
  • A. Medina chosen
    Medina is a holy city in western Saudi Arabia that is revered in Islam as the site of the Prophet Muhammad’s mosque and tomb and the second-holiest city after Mecca.
  • B. Medina
    Medina is an affluent residential city on the eastern shore of Lake Washington in Washington State, known for its waterfront homes and as the home of several prominent tech executives.
  • C. Medina
    Medina is a small suburban city in Minnesota known for its rural character, parks, and proximity to the Minneapolis–Saint Paul metropolitan area.
  • D. Medina
    Medina is a coastal municipality in the Philippines known for its scenic shoreline along Macajalar Bay and its largely rural, agriculture-based communities.
  • E. Medina
    Medina is a small unincorporated community and census-designated place in Bandera County, Texas, known for its rural Hill Country setting and apple orchards.
  • F. None of above.

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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e5e43d48190a8fd367f13f1c7e1 completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c55fa248190b114a5b63560f87b completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff50020d748190be36f3c08df43e40 completed May 9, 2026, 3:17 p.m.
NED2 Entity disambiguation (via description) batch_69ff50a349688190ab7a18fa4460d86e completed May 9, 2026, 3:20 p.m.
Created at: April 10, 2026, 4:12 a.m.