Triple
T23247859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James FitzGerald, 1st Duke of Leinster |
E581631
|
entity |
| Predicate | elevatedToDukedom |
P151533
|
FINISHED |
| Object | 1766 |
—
|
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: 1766 | Statement: [James FitzGerald, 1st Duke of Leinster, elevatedToDukedom, 1766]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: elevatedToDukedom Context triple: [James FitzGerald, 1st Duke of Leinster, elevatedToDukedom, 1766]
-
A.
elevatedToDuchy
Indicates that a territory, region, or domain has been formally raised in rank or status to become a duchy.
-
B.
elevatedToDuchess
Indicates that a person was formally raised or promoted to the noble rank or title of duchess.
-
C.
elevatedToArchduchy
Indicates that an entity’s status or rank has been raised to that of an archduchy.
-
D.
elevatedToMarquessate
Indicates that an individual or title has been formally raised in rank to the status of a marquessate.
-
E.
elevatedToPeerageFor
Indicates that a person was granted a noble title or peerage specifically as a result of, or in recognition for, a particular reason, action, or service.
- F. None of above. chosen
Provenance (4 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f3a67c81908ed18480e1cccc29 |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
| PDg | Predicate description generation | batch_69f01d8770d081908897c28b04e5faea |
completed | April 28, 2026, 2:37 a.m. |
Created at: April 17, 2026, 4:10 p.m.