Triple
T4318621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erskine May: Parliamentary Practice |
E96454
|
entity |
| Predicate | latestEditionNumber |
P10601
|
FINISHED |
| Object | 25 |
—
|
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: 25 | Statement: [Erskine May: Parliamentary Practice, latestEditionNumber, 25]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: latestEditionNumber Context triple: [Erskine May: Parliamentary Practice, latestEditionNumber, 25]
-
A.
lastEdition
chosen
Indicates that one entity is the most recent or final edition/version within a series or sequence of editions.
-
B.
editionNumber
Indicates the specific sequential number assigned to an edition of a work within its series of published versions.
-
C.
latestVersion
Indicates that one entity is the most recent or up-to-date version of another entity within a sequence or set of versions.
-
D.
nextEdition
Indicates that one entity is the immediate subsequent edition or version that follows another in a sequence.
-
E.
latestMinorVersion
Indicates that one version is the most recent minor (non-major) update within the series of versions derived from another version.
- 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_69b345422aac81909ddbadae437d122e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350f883c88190a2d72f7d124eef43 |
completed | March 12, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69b34f4bec888190987fc2631498b637 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:12 p.m.