Triple

T10890507
Position Surface form Disambiguated ID Type / Status
Subject Emma Donoghue E257159 entity
Predicate wrote P2831 FINISHED
Object Akin E892198 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: Akin | Statement: [Emma Donoghue, wrote, Akin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akin
Context triple: [Emma Donoghue, wrote, Akin]
  • A. Akin chosen
    Akin is a novel by Irish-Canadian author Emma Donoghue that explores family, memory, and the legacy of World War II through the unexpected relationship between an elderly man and his young great-nephew on a trip to France.
  • B. Arkin
    Arkin is a surname most notably associated with the late American actor and filmmaker Alan Arkin.
  • C. Aikin
    Aikin is the family name of the prominent 18th–19th century English literary and intellectual family to which writer and educator Anna Laetitia Barbauld belonged.
  • D. Aykah
    Aykah is a community mentioned in Islamic tradition as the people to whom the prophet Shu'ayb was sent, known for their wrongdoing and subsequent divine punishment.
  • E. Aliko
    Aliko is the first name of Aliko Dangote, a Nigerian billionaire industrialist and one of Africa’s most prominent business magnates.
  • 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_69d6aa848804819081b2713ca0bedf06 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d752041e2c8190b513dc9dc5857fcc completed April 9, 2026, 7:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2169ea02c8190addf125ec5adafe8 completed April 17, 2026, 11:16 a.m.
Created at: April 8, 2026, 9:21 p.m.