Triple
T1915325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toby Ziegler |
E40003
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | The White House |
E323
|
NE 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: The White House | Statement: [Toby Ziegler, employer, The White House]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The White House Context triple: [Toby Ziegler, employer, The White House]
-
A.
White House
chosen
The White House is the official residence and primary workplace of the president of the United States, located at 1600 Pennsylvania Avenue in Washington, D.C.
-
B.
La Casa Blanca
La Casa Blanca is a famous nickname for Real Madrid CF, highlighting the Spanish football club’s iconic all-white kit and storied prestige.
-
C.
Oval Office
The Oval Office is the distinctive, oval-shaped working office of the President of the United States and a central symbol of the American presidency.
-
D.
Executive Mansion
The Executive Mansion is the official residence and principal workplace of the President of Liberia, located in the capital city of Monrovia.
-
E.
Presidentinlinna
Presidentinlinna is the official residence and workplace of the President of Finland, located in central Helsinki.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a8864298748190a2f2fd34f7ef8d77 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb1e517e8819086e4bf5a305aeb25 |
completed | March 7, 2026, 5:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adf3da81308190a49844a8ac2997da |
completed | March 8, 2026, 10:10 p.m. |
Created at: March 4, 2026, 7:35 p.m.