Triple
T6133420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Earl of Derby (first term as Prime Minister) |
E136772
|
entity |
| Predicate | sequenceInOfficeForDerby |
P2953
|
FINISHED |
| Object | first of three Derby ministries |
—
|
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: first of three Derby ministries | Statement: [The Earl of Derby (first term as Prime Minister), sequenceInOfficeForDerby, first of three Derby ministries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sequenceInOfficeForDerby Context triple: [The Earl of Derby (first term as Prime Minister), sequenceInOfficeForDerby, first of three Derby ministries]
-
A.
ordinalInOffice
chosen
Indicates the numerical order or rank of an individual’s term or tenure in a particular office or position.
-
B.
orderOfDeputies
Indicates the hierarchical sequence or ranking of deputies within a governing or organizational structure.
-
C.
sequenceInCommonwealthGames
Indicates that an entity occupies a specific position or order within the sequence of Commonwealth Games events or editions.
-
D.
sequenceInWork
Indicates that one work appears as a sequential part or installment within a larger overarching work.
-
E.
sequenceInGames
Indicates that one game or event occurs as part of an ordered sequence within a series of games.
- 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_69c008a0a37c81908e5b4f879158afb3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05c509848819089a2b2b58744bc25 |
completed | March 22, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69c055f19b0c81908be34a00ab218723 |
completed | March 22, 2026, 8:49 p.m. |
Created at: March 22, 2026, 4:15 p.m.