Triple
T5423913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paradise Lost |
E121316
|
entity |
| Predicate | numberOfBooksOriginalEdition |
P17539
|
FINISHED |
| Object | 10 |
—
|
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: 10 | Statement: [Paradise Lost, numberOfBooksOriginalEdition, 10]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfBooksOriginalEdition Context triple: [Paradise Lost, numberOfBooksOriginalEdition, 10]
-
A.
numberOfEditions
Indicates the total count of distinct editions associated with a given entity.
-
B.
survivingCopiesOfFirstEdition
Indicates that the subject has or is associated with copies that remain extant from the first edition of a work.
-
C.
numberOfBooks
Indicates the quantity of books associated with a given entity.
-
D.
firstEditionVolumes
chosen
Indicates that the subject is a work or publication and the object is the number of volumes in its first edition.
-
E.
hasFirstEditionYear
Indicates the year in which the first edition of an item (such as a work, book, or publication) was originally released or published.
- 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_69bd463b58d88190b258261573de9e91 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8812f84c819094d8516f69fff83d |
completed | March 20, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69bd8469f5e48190bbe5c8bdfe8925ea |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:06 p.m.