Triple

T19146682
Position Surface form Disambiguated ID Type / Status
Subject Mariel Margaret Hamm E468696 entity
Predicate givenName P17 FINISHED
Object Mariel E123214 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: Mariel | Statement: [Mariel Margaret Hamm, givenName, Mariel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mariel
Context triple: [Mariel Margaret Hamm, givenName, Mariel]
  • A. Mariel chosen
    Mariel is a Cuban port city best known as the departure point for the 1980 Mariel boatlift, during which thousands of Cubans emigrated to the United States.
  • B. Tusa
    Tusa is a surname most notably associated with Sir John Tusa, a prominent British arts administrator and former broadcaster.
  • C. Tusa
    "Tusa" is a globally popular reggaeton and Latin pop song by Colombian singer Karol G featuring Nicki Minaj, known for its catchy melody and themes of heartbreak and empowerment.
  • D. Barden
    Barden is a small village in North Yorkshire, England, known for its scenic location in Wharfedale within the Yorkshire Dales.
  • E. Somosta
    Somosta is a town located within Egypt's Beni Suef Governorate, known as one of the local urban centers in this Upper Egyptian region.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e9796ebc8190928f4b227685bc33 completed April 20, 2026, 8:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a06f25067b0819097fbe77b322eee36 completed May 15, 2026, 10:15 a.m.
Created at: April 10, 2026, 12:06 p.m.