Triple
T4741162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidential Office Building |
E105243
|
entity |
| Predicate | restorationCompletionDate |
P8589
|
FINISHED |
| Object | 1948 |
—
|
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: 1948 | Statement: [Presidential Office Building, restorationCompletionDate, 1948]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: restorationCompletionDate Context triple: [Presidential Office Building, restorationCompletionDate, 1948]
-
A.
reconstructionOrRestorationDate
chosen
Indicates the date on which an entity was reconstructed or restored after damage, alteration, or deterioration.
-
B.
reconstructionEndDate
Indicates the date on which a reconstruction process or project is completed.
-
C.
restorationEnd
Indicates the point in time or condition at which a restoration process or restorative state comes to an end.
-
D.
repairDate
Indicates the date on which a repair action was performed or is scheduled to be performed on an entity.
-
E.
originalCompletionDate
Indicates the date on which something was first completed, before any subsequent changes, revisions, or updates.
- 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_69bd43ef87a48190a5bc3600711aa032 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64a5f3548190a6acf1dcfd64d11d |
completed | March 20, 2026, 3:15 p.m. |
| PD | Predicate disambiguation | batch_69bd6221c3b881908604f35f8de6f16b |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:19 p.m.