Triple
T34997019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baron Wodehouse |
E1009564
|
entity |
| Predicate | elevatedHolderTo |
P109561
|
FINISHED |
| Object | Earl of Kimberley |
—
|
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: Earl of Kimberley | Statement: [Baron Wodehouse, elevatedHolderTo, Earl of Kimberley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: elevatedHolderTo Context triple: [Baron Wodehouse, elevatedHolderTo, Earl of Kimberley]
-
A.
elevationOfHolder
Indicates the vertical distance or height of the holder relative to a reference level (such as ground or sea level).
-
B.
elevationHolder
Indicates that one entity serves as the reference or container for the elevation (height above a baseline) associated with another entity.
-
C.
elevatedTo
Indicates that one entity is promoted or raised to a higher rank, status, position, or level relative to another.
-
D.
erectedTo
Indicates that something has been constructed or set up for the purpose of honoring, commemorating, or serving a particular entity or objective.
-
E.
raisedTo
chosen
Indicates that one entity has been elevated, lifted, or brought up to a higher level, position, or state by another 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_69f76dca50dc8190b71f39defe186be8 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:01 p.m.