Triple
T8495244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Downward to the Earth |
E201081
|
entity |
| Predicate | hasAlternateEdition |
P44721
|
FINISHED |
| Object | paperback edition |
—
|
LITERAL 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: paperback edition | Statement: [Downward to the Earth, hasAlternateEdition, paperback edition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlternateEdition Context triple: [Downward to the Earth, hasAlternateEdition, paperback edition]
-
A.
hasDifferentEditions
Indicates that an entity exists in multiple distinct versions or editions that differ in some characteristics.
-
B.
hasEditionIn
chosen
Indicates that one entity has a specific edition or version that exists or is available in another entity (such as a particular format, language, or location).
-
C.
hasAlternateExperience
Indicates that an entity is associated with a different or substitute experience relative to a primary or standard one.
-
D.
hasEnglishEdition
Indicates that one entity has a version or edition of itself that is produced or available in the English language.
-
E.
hasAlternateCut
Indicates that an entity has an alternative edited version or cut, distinct from its primary or original form.
- 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_69ca831ee390819095fae73400bbfafc |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe57c01f881908cb77c8c834ac08d |
completed | March 31, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69cbd10a4b0881909e254117780dc823 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:13 p.m.