Triple
T38055366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parliament of 1626 |
E949884
|
entity |
| Predicate | keyFigureInLords |
P139401
|
FINISHED |
| Object | George Villiers, 1st Duke of Buckingham |
—
|
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: George Villiers, 1st Duke of Buckingham | Statement: [Parliament of 1626, keyFigureInLords, George Villiers, 1st Duke of Buckingham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyFigureInLords Context triple: [Parliament of 1626, keyFigureInLords, George Villiers, 1st Duke of Buckingham]
-
A.
lordOf
Indicates that one entity holds lordship, authority, or dominion over another entity.
-
B.
borderLord
Indicates that one entity serves as the feudal or territorial lord presiding over a border or frontier region associated with another entity.
-
C.
firstKnownLord
Indicates that the subject is the earliest historically or canonically recorded lord associated with the object.
-
D.
powerBehindThrone
Indicates a relationship where one entity secretly or informally controls or strongly influences the authority and decisions of another entity that holds the official position of power.
-
E.
keyFigureMentioned
chosen
Indicates that a central or important person related to the context has been explicitly referenced.
- 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_69f76f000cf081908c11fb5443b392e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.