Triple
T19918412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zoo City |
E478724
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Lauren Beukes |
—
|
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: Lauren Beukes | Statement: [Zoo City, author, Lauren Beukes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lauren Beukes Context triple: [Zoo City, author, Lauren Beukes]
-
A.
Lauren Beukes
chosen
Lauren Beukes is a South African author known for her genre-blending speculative fiction novels such as "Zoo City" and "The Shining Girls."
-
B.
Carl Beukes
Carl Beukes is a South African actor known for his work in film and television, including roles in international productions.
-
C.
Madeleine Le Roux
Madeleine Le Roux is an actress best known for her work in American film and television during the 1970s, including roles in offbeat comedies and genre productions.
-
D.
Sarah Pinborough
Sarah Pinborough is a British author known for her twist-filled psychological thrillers and dark fantasy novels.
-
E.
Naomi Alderman
Naomi Alderman is a British novelist and game writer best known for her award-winning speculative novel "The Power" and her explorations of religion, power, and gender in contemporary fiction.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c3d990819089386d9f30323e8c |
completed | April 20, 2026, 4:52 p.m. |
Created at: April 10, 2026, 1:53 p.m.