Triple
T25468315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Atrocity Archives |
E638231
|
entity |
| Predicate | publisherForUKEdition |
P29558
|
FINISHED |
| Object | Orbit Books |
—
|
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: Orbit Books | Statement: [The Atrocity Archives, publisherForUKEdition, Orbit Books]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publisherForUKEdition Context triple: [The Atrocity Archives, publisherForUKEdition, Orbit Books]
-
A.
publisherOfEnglishEdition
Indicates that an entity serves as the publisher responsible for the English-language edition of another work or resource.
-
B.
publisherInUnitedStates
Indicates that the publisher associated with an entity is located in, or operates from, the United States.
-
C.
firstUKPublisher
chosen
Indicates that the subject was the first entity to publish the object in the United Kingdom.
-
D.
countryOfPublication
Indicates the country in which a work was formally published or made publicly available.
-
E.
englishEditionEditor
Indicates that the subject is the person or entity responsible for editing the English-language edition of the object.
- F. None of above.
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_69e75db9b964819096802dcf502e577e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 21, 2026, 2:20 p.m.