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.