Triple
T16139461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tales from Earthsea |
E391613
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | Orion Books |
E57986
|
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: Orion Books | Statement: [Tales from Earthsea, publisher, Orion Books]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orion Books Context triple: [Tales from Earthsea, publisher, Orion Books]
-
A.
Orbit Books
Orbit Books is a major science fiction and fantasy publishing imprint known for releasing works by prominent genre authors worldwide.
-
B.
Orion Publishing Group
chosen
Orion Publishing Group is a major British book publisher known for its wide-ranging fiction and non-fiction imprints and as part of the Hachette UK group.
-
C.
Mariner Books
Mariner Books is a publishing imprint known for producing a wide range of literary fiction, nonfiction, and classic reprints.
-
D.
Voyager Books
Voyager Books is a science fiction and fantasy imprint of HarperCollins known for publishing major genre authors and series.
-
E.
Hyperion Books
Hyperion Books is an American publishing imprint, originally founded by The Walt Disney Company, known for releasing a wide range of popular fiction and non-fiction titles.
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21a06e0988190b5cd62d422d058a2 |
completed | April 17, 2026, 11:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff2b75988819094baaff8f53f48ce |
completed | May 10, 2026, 2:51 a.m. |
Created at: April 10, 2026, 5:01 a.m.