Triple
T28642024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Henry Wellesley, 2nd Earl Cowley |
E724951
|
entity |
| Predicate | date of succession |
P47970
|
FINISHED |
| Object | 1884 |
—
|
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: 1884 | Statement: [William Henry Wellesley, 2nd Earl Cowley, date of succession, 1884]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: date of succession Context triple: [William Henry Wellesley, 2nd Earl Cowley, date of succession, 1884]
-
A.
dateOfSuccession
chosen
Indicates the specific date on which one entity formally succeeded or took over a role, position, or title from another.
-
B.
successionLawChangeYear
Indicates the year in which a change to the rules or laws governing succession took effect.
-
C.
successorAdoptionYear
Indicates the year in which a successor entity formally adopted or took over from its predecessor.
-
D.
timeOfAccession
Indicates the specific time at which an entity formally assumes a position, role, or status.
-
E.
successionYear
Indicates the calendar year in which one entity formally succeeded or took over from another in a given role, position, or status.
- 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_69f01d8423888190bd2f4e52605bf261 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:45 a.m.