Triple

T1360041
Position Surface form Disambiguated ID Type / Status
Subject Hispaniola E29077 entity
Predicate containsCity P294 FINISHED
Object Port-au-Prince E29318 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: Port-au-Prince | Statement: [Hispaniola, containsCity, Port-au-Prince]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port-au-Prince
Context triple: [Hispaniola, containsCity, Port-au-Prince]
  • A. Port-au-Prince chosen
    Port-au-Prince is the capital and largest city of Haiti, serving as the country’s political, economic, and cultural center.
  • B. Pétion-Ville
    Pétion-Ville is a suburban commune in the hills southeast of Port-au-Prince, known as one of Haiti’s main residential and commercial centers.
  • C. Croix-des-Bouquets
    Croix-des-Bouquets is a commune in Haiti known for its vibrant metal art tradition and proximity to the capital, Port-au-Prince.
  • D. Roseau
    Roseau is the largest city and main commercial and administrative center of the Caribbean island nation of Dominica.
  • E. Port of Spain
    Port of Spain is the capital city and main commercial and cultural center of Trinidad and Tobago, located on the northwest coast of the island of Trinidad.
  • 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_69a498d77abc8190913bf57e5f51d2c4 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c2b156b081909c99ada70a969fc0 completed March 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ace566694c81909b07143855014884 completed March 8, 2026, 2:56 a.m.
Created at: March 1, 2026, 7:56 p.m.