Triple
T1666676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Buildings |
E36027
|
entity |
| Predicate | formerlyHousedOfficeOf |
P17674
|
FINISHED |
| Object | Prime Minister of the Union of South Africa |
—
|
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 Union of South Africa | Statement: [Union Buildings, formerlyHousedOfficeOf, Prime Minister of the Union of South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerlyHousedOfficeOf Context triple: [Union Buildings, formerlyHousedOfficeOf, Prime Minister of the Union of South Africa]
-
A.
officePreviouslyHeldBy
Indicates that a particular office or position was formerly occupied by a specified person or entity.
-
B.
servesAsOfficeOf
chosen
Indicates that one entity functions as the official office, headquarters, or administrative base for another entity.
-
C.
hasOffice
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
-
D.
successorOfficeTo
Indicates that one office or position directly follows and replaces another in an official sequence or hierarchy.
-
E.
typeOfOffice
Indicates the specific category or kind of office that an office entity belongs to (e.g., executive, legislative, judicial, or other office types).
- 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_69a8861286808190939afff3ce8ee31e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa994f92b0819084ee2f6a672334b9 |
completed | March 6, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69a907d2475c8190b7ec7dccd3335eb1 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.