Triple

T2824248
Position Surface form Disambiguated ID Type / Status
Subject Havana Bay E54882 entity
Predicate adjacentTo P224 FINISHED
Object Regla
Regla is a coastal municipality of Havana, Cuba, known for its port, Afro-Cuban religious traditions, and location across the bay from Old Havana.
 E301158 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: Regla | Statement: [Havana Bay, adjacentTo, Regla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Regla
Context triple: [Havana Bay, adjacentTo, Regla]
  • A. Kural
    Kural is the common short name for the Tirukkural, a classic Tamil text of concise couplets on ethics, governance, and love.
  • B. Break Every Rule
    "Break Every Rule" is a 1986 studio album by Tina Turner that continued her successful solo comeback with a mix of pop-rock and soulful ballads.
  • C. Guarda
    Guarda is a historic city in central Portugal known for being the country's highest-altitude city and for its well-preserved medieval architecture.
  • D. La Raza
    La Raza is a major Mexico City Metro transfer station known for its high passenger traffic and connections between multiple lines.
  • E. 8 Simple Rules
    8 Simple Rules is an American sitcom that follows a suburban father struggling to cope with his teenage daughters, originally starring John Ritter and later featuring James Garner.
  • 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: Regla
Triple: [Havana Bay, adjacentTo, Regla]
Generated description
Regla is a coastal municipality of Havana, Cuba, known for its port, Afro-Cuban religious traditions, and location across the bay from Old Havana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Regla
Target entity description: Regla is a coastal municipality of Havana, Cuba, known for its port, Afro-Cuban religious traditions, and location across the bay from Old Havana.
  • A. Kural
    Kural is the common short name for the Tirukkural, a classic Tamil text of concise couplets on ethics, governance, and love.
  • B. Break Every Rule
    "Break Every Rule" is a 1986 studio album by Tina Turner that continued her successful solo comeback with a mix of pop-rock and soulful ballads.
  • C. Guarda
    Guarda is a historic city in central Portugal known for being the country's highest-altitude city and for its well-preserved medieval architecture.
  • D. La Raza
    La Raza is a major Mexico City Metro transfer station known for its high passenger traffic and connections between multiple lines.
  • E. 8 Simple Rules
    8 Simple Rules is an American sitcom that follows a suburban father struggling to cope with his teenage daughters, originally starring John Ritter and later featuring James Garner.
  • 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_69ab49e100c0819082a40cb797383243 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde91487881909989c08bbf76f0da completed March 7, 2026, 8:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69afcead12588190bfbb2c9e93b05e0d completed March 10, 2026, 7:56 a.m.
NEDg Description generation batch_69afcf5ec0a481909061d50877429f3b completed March 10, 2026, 7:59 a.m.
NED2 Entity disambiguation (via description) batch_69afcff778748190978e7d306e0d1ce1 completed March 10, 2026, 8:01 a.m.
Created at: March 6, 2026, 9:59 p.m.