Triple
T26391396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Long Walk, Windsor |
E663420
|
entity |
| Predicate | laterImprovedUnder |
P180205
|
FINISHED |
| Object | King George III |
—
|
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: King George III | Statement: [Long Walk, Windsor, laterImprovedUnder, King George III]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterImprovedUnder Context triple: [Long Walk, Windsor, laterImprovedUnder, King George III]
-
A.
hasImproved
Indicates that an entity’s state, quality, or performance has become better compared to a previous point in time.
-
B.
improvesIn
Indicates that one entity causes or contributes to an increase in quality, performance, or effectiveness in another entity or context.
-
C.
improvesOn
Indicates that one entity enhances, refines, or performs better than another entity, typically by addressing its limitations or increasing its effectiveness.
-
D.
laterRaised
Indicates that one entity was raised, elevated, or brought up at a time subsequent to another referenced event or state.
-
E.
laterHelps
Indicates that one entity provides help or assistance to another at a subsequent time rather than immediately.
- 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_69ee883823988190b418b111be28a44a |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f739a638748190808e7a2930dce16e |
completed | May 3, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f732f2dc6c8190a4e86da98cc5eb05 |
completed | May 3, 2026, 11:35 a.m. |
| PDg | Predicate description generation | batch_69f739a58b3c81908abc2b8738a65678 |
completed | May 3, 2026, 12:03 p.m. |
Created at: April 26, 2026, 11:26 p.m.