Triple
T20751072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viscount Macmillan of Ovenden |
E510717
|
entity |
| Predicate | firstHolderOffice |
P4891
|
FINISHED |
| Object | Prime Minister of the United Kingdom |
—
|
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: Prime Minister of the United Kingdom | Statement: [Viscount Macmillan of Ovenden, firstHolderOffice, Prime Minister of the United Kingdom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstHolderOffice Context triple: [Viscount Macmillan of Ovenden, firstHolderOffice, Prime Minister of the United Kingdom]
-
A.
firstOfficeHolder
chosen
Indicates that the subject is the very first individual to hold a particular office or position associated with the object.
-
B.
firstHolderParty
Indicates that the referenced party is the initial or original holder in the specified relationship or arrangement.
-
C.
firstOfficeHolderStart
Indicates the date or time when the first person to hold a particular office or position began their term.
-
D.
respondentOffice
Indicates the office or organizational unit that serves as the respondent in a given case, inquiry, or interaction.
-
E.
signatoryOffice
Indicates the office or organizational unit that formally signs or authorizes a document, agreement, or record.
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c22ad0c8819087a8db2bac8dd408 |
completed | April 21, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c0509608819080cdbf47fcddfe36 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:34 p.m.