Triple
T19219573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bush House |
E480574
|
entity |
| Predicate | BBCWorldServiceOccupancyStart |
P98195
|
FINISHED |
| Object | 1941 |
—
|
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: 1941 | Statement: [Bush House, BBCWorldServiceOccupancyStart, 1941]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BBCWorldServiceOccupancyStart Context triple: [Bush House, BBCWorldServiceOccupancyStart, 1941]
-
A.
inauguralOccupancy
chosen
Indicates that an entity is the first occupant or user of a place, structure, or asset.
-
B.
hostOccupation
Indicates that one entity serves as the primary job, profession, or role held by another entity.
-
C.
hasOccupancyStatus
Indicates the current usage or availability state of something, such as whether it is occupied, vacant, or otherwise in use.
-
D.
officeStartTime (United States Secretary of Health and Human Services)
Indicates the date and time at which an individual officially begins their term as United States Secretary of Health and Human Services.
-
E.
officeStartTime (Administrator of UNDP)
Indicates the date and time at which the person began serving as Administrator of UNDP.
- 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa3d5684819092d3083f65ea90d5 |
completed | April 20, 2026, 10:04 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:23 p.m.