Triple
T31988038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lebor Gabála Érenn |
E816787
|
entity |
| Predicate | hasScholarlyEditor |
P114311
|
FINISHED |
| Object | R. A. Stewart Macalister |
—
|
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: R. A. Stewart Macalister | Statement: [Lebor Gabála Érenn, hasScholarlyEditor, R. A. Stewart Macalister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasScholarlyEditor Context triple: [Lebor Gabála Érenn, hasScholarlyEditor, R. A. Stewart Macalister]
-
A.
hasScholarlyEdition
Indicates that an entity has an associated scholarly (critically edited and annotated) edition prepared according to academic standards.
-
B.
isScholarly
Indicates that an entity exhibits characteristics of academic rigor, research-based inquiry, and adherence to scholarly standards or conventions.
-
C.
hasEditorialBoard
Indicates that an entity (such as a publication or journal) is overseen or governed by a specific editorial board.
-
D.
hasEditorialWork
chosen
Indicates that one entity performs, contributes to, or is responsible for editorial work on another entity.
-
E.
hasNotableScholar
Indicates that an entity is associated with a scholar who is recognized as particularly distinguished or influential in relation to that entity.
- 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_69f348f8002081909a3588758ba94afb |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 1, 2026, 12:12 a.m.