Triple
T28359319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord Keeper |
E718318
|
entity |
| Predicate | wasEventually |
P120479
|
FINISHED |
| Object | merged in practice with the office of Lord Chancellor |
—
|
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: merged in practice with the office of Lord Chancellor | Statement: [Lord Keeper, wasEventually, merged in practice with the office of Lord Chancellor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasEventually Context triple: [Lord Keeper, wasEventually, merged in practice with the office of Lord Chancellor]
-
A.
eventuallyIn
chosen
Indicates that one entity will, at some later time or in the long run, come to be located in, belong to, or be contained within another entity or state.
-
B.
wasA
Indicates that an entity previously had a certain role, type, or classification in the past.
-
C.
wasLast
Indicates that one entity occurred or appeared after all others in a sequence, making it the final item or event.
-
D.
wonAt
Indicates that one entity achieved victory or success in a specific event, competition, or context.
-
E.
wasIn
Indicates that an entity existed, occurred, or was located within a particular place or context during a specified time or situation.
- 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_69eff6ed5af48190be4e0adf298223e0 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c3048248190b55266211394ecb7 |
completed | May 2, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 12:51 a.m.