Triple

T14368233
Position Surface form Disambiguated ID Type / Status
Subject Afonso Costa E356289 entity
Predicate givenName P17 FINISHED
Object Afonso E565702 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: Afonso | Statement: [Afonso Costa, givenName, Afonso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Afonso
Context triple: [Afonso Costa, givenName, Afonso]
  • A. Afonso chosen
    Afonso is a Portuguese surname most notably borne by the renowned geometric abstractionist painter and architect Nadir Afonso.
  • B. António
    António is a common Portuguese given name, notably borne by António Guterres, the Secretary-General of the United Nations.
  • C. Afonso Gonçalves
    Afonso Gonçalves was a Portuguese sailor and explorer who served in the pioneering early voyages of Portugal’s maritime expansion to India.
  • D. Sebastian of Portugal
    Sebastian of Portugal was the young and zealous 16th-century king whose disastrous 1578 crusading campaign in Morocco led to his death and a dynastic crisis that precipitated the Iberian Union under Spanish rule.
  • E. Manuel of Braganza
    Manuel of Braganza was a 17th-century Portuguese infante of the House of Braganza, notable as a younger son of King John IV of Portugal and Queen Luisa de Guzmán.
  • 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8faf00e8819087d7100e9d8c1877 completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fec86c6c6c8190957e398e3dcdd840 completed May 9, 2026, 5:38 a.m.
Created at: April 10, 2026, 1:15 a.m.