Triple
T22874096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swordheart |
E567274
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | T. Kingfisher |
—
|
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: T. Kingfisher | Statement: [Swordheart, author, T. Kingfisher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T. Kingfisher Context triple: [Swordheart, author, T. Kingfisher]
-
A.
T. Kingfisher
chosen
T. Kingfisher is the pen name of American author Ursula Vernon, known for her acclaimed fantasy and horror fiction for both adults and young adults.
-
B.
Jazmyn Simon
Jazmyn Simon is an American actress known for her roles on television series such as "Ballers" and "Psych: The Movie."
-
C.
Tessa Dahl
Tessa Dahl is a British author and former actress, known for her novels and as the daughter of writer Roald Dahl and actress Patricia Neal.
-
D.
Catherynne M. Valente
Catherynne M. Valente is an American speculative fiction author known for her lush, experimental prose and genre-blending works that often draw on myth, folklore, and fairy tales.
-
E.
Emily M. Danforth
Emily M. Danforth is an American novelist best known for her acclaimed coming-of-age LGBTQ+ novel "The Miseducation of Cameron Post."
- 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_69e24589d8348190b96422d13a678bc1 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f56d6448190ada4aef08eac2bed |
completed | April 29, 2026, 3:47 a.m. |
Created at: April 17, 2026, 3:39 p.m.