Triple

T9513451
Position Surface form Disambiguated ID Type / Status
Subject Calle 23 (La Rampa) E229459 entity
Predicate connectsTo P845 FINISHED
Object Calle L E238529 NE FINISHED

How this triple was built (2 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: Calle L | Statement: [Calle 23 (La Rampa), connectsTo, Calle L]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calle L
Context triple: [Calle 23 (La Rampa), connectsTo, Calle L]
  • A. Calle Línea chosen
    Calle Línea is a principal thoroughfare running through Havana’s Vedado district, known for its historic architecture and cultural significance.
  • B. Calle Cerrito
    Calle Cerrito is a central street in Buenos Aires, Argentina, known for running past major landmarks in the city’s downtown area.
  • C. Calle del Carmen
    Calle del Carmen is a busy pedestrian shopping street in central Madrid, known for its stores, cafés, and proximity to the Puerta del Sol.
  • D. Calle del León
    Calle del León is a historic street in central Madrid, Spain, known for its cultural institutions and literary heritage.
  • E. Calle San José
    Calle San José is a historic street in Old San Juan, Puerto Rico, known for its colonial architecture, cultural landmarks, and vibrant local commerce.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84777560819084cddd999badc1aa completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd986aa99c8190b2eaa7f9b111aa2e completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d13a3e93a481908569a4ec80c834ab completed April 4, 2026, 4:20 p.m.
Created at: March 30, 2026, 7:58 p.m.