Triple

T20973935
Position Surface form Disambiguated ID Type / Status
Subject Manuel da Costa E516574 entity
Predicate familyName P18 FINISHED
Object da Costa NE NERFINISHED

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: da Costa | Statement: [Manuel da Costa, familyName, da Costa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: da Costa
Context triple: [Manuel da Costa, familyName, da Costa]
  • A. da Costa chosen
    da Costa is a Portuguese surname borne by numerous notable individuals across literature, politics, sports, and other fields.
  • B. Carlos da Costa
    Carlos da Costa is a personal name shared by multiple individuals, typically of Portuguese or Brazilian origin, whose specific notable achievements are not uniquely identifiable from this context.
  • C. da Costa Gomes
    da Costa Gomes is the Portuguese surname of Francisco da Costa Gomes, a prominent 20th-century military officer and former President of Portugal.
  • D. Salvador da Costa
    Salvador da Costa is a Portuguese politician best known as one of the founders of the Portuguese Socialist Party.
  • E. Jorge Costa
    Jorge Costa is a retired Portuguese central defender and football manager best known for his long and successful playing career with FC Porto and the Portugal national team.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4fee5ac8190875fa9ceba1a5e5e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fba2406c8190bd75dec585c14bfa completed April 21, 2026, 4:22 a.m.
Created at: April 16, 2026, 1:45 p.m.