Triple
T25270653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OS Explorer OL1 |
E633558
|
entity |
| Predicate | sheetNumber |
P120918
|
FINISHED |
| Object | OL1 |
—
|
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: OL1 | Statement: [OS Explorer OL1, sheetNumber, OL1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sheetNumber Context triple: [OS Explorer OL1, sheetNumber, OL1]
-
A.
numberOfSheets
Indicates the quantity of individual sheets associated with or contained in an entity.
-
B.
codePageNumber
Indicates the specific page number within a code document or code listing where something is located or referenced.
-
C.
documentNumber
Indicates the unique identifying number assigned to a specific document in the relationship.
-
D.
numberingStatus
Indicates the status or condition of an entity’s assigned number or numbering process (e.g., whether it has been numbered, is pending, or has a particular numbering state).
-
E.
pageNumber
chosen
Indicates the specific numerical position of a page within an ordered sequence of pages.
- 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_69e75a92f48881909974ff9c11150a2e |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48ba1a1f88190b3db79ec06bfa994 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 1:16 p.m.