Triple
T27995503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Nathaniel Curzon |
E707000
|
entity |
| Predicate | laterHeldTitle |
P22452
|
FINISHED |
| Object | Marquess Curzon of Kedleston |
—
|
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: Marquess Curzon of Kedleston | Statement: [George Nathaniel Curzon, laterHeldTitle, Marquess Curzon of Kedleston]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterHeldTitle Context triple: [George Nathaniel Curzon, laterHeldTitle, Marquess Curzon of Kedleston]
-
A.
laterTitleHolder
chosen
Indicates that one entity is a subsequent holder of a particular title or position previously held by another entity.
-
B.
titleHeldAfter
Indicates that one entity held a particular title or position after another entity, establishing a temporal succession in holding that title.
-
C.
titleHeldTo
Indicates that one entity holds or possesses a specific title in relation to another entity or context.
-
D.
heldTitleUntil
Indicates that an entity possessed or held a specific title or position continuously up to a particular end date or point in time.
-
E.
titleHeldThrough
Indicates that an entity holds or possesses a title by means of, or via the intermediary of, another entity or mechanism.
- 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_69ef96b980d88190a753b2f9a978595a |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fd44474ed48190ac372e4c88d762ed |
completed | May 8, 2026, 2:02 a.m. |
| PD | Predicate disambiguation | batch_69fd41ef28a48190a66959be5c964461 |
completed | May 8, 2026, 1:52 a.m. |
Created at: April 27, 2026, 7:53 p.m.