Triple

T12273142
Position Surface form Disambiguated ID Type / Status
Subject Steve Biko E292520 entity
Predicate familyName P18 FINISHED
Object Biko E209043 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: Biko | Statement: [Steve Biko, familyName, Biko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Biko
Context triple: [Steve Biko, familyName, Biko]
  • A. Biko chosen
    "Biko" is a politically charged protest song by Peter Gabriel that commemorates South African anti-apartheid activist Steve Biko and helped raise global awareness of apartheid.
  • B. Quiapo
    Quiapo is a historic and densely populated district in Manila, Philippines, known for its bustling markets, the Quiapo Church, and its role as a major commercial and transport hub.
  • C. Blanquillos
    Blanquillos is a popular nickname for the Spanish football club Real Zaragoza, referring to the team’s traditional white kit.
  • D. Robacio
    Robacio is a Spanish-language surname, notably borne by the Argentine military officer Carlos Robacio.
  • E. Bombo
    Bombo is a 1934 American comedy film starring the British music hall duo Flanagan and Allen, known for its lighthearted musical numbers and slapstick humor.
  • 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_69d6ab6856488190b5d31178d5015f8e completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cee7158819093fff74db6867896 completed April 10, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e6b50a48190b1beabd149d5830f completed May 2, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:52 p.m.