Triple
T554680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palace of Whitehall |
E11915
|
entity |
| Predicate | currentUseOfSite |
P15047
|
FINISHED |
| Object | government buildings on Whitehall |
—
|
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: government buildings on Whitehall | Statement: [Palace of Whitehall, currentUseOfSite, government buildings on Whitehall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentUseOfSite Context triple: [Palace of Whitehall, currentUseOfSite, government buildings on Whitehall]
-
A.
site
Indicates that one entity is the physical or virtual location where another entity is situated, occurs, or is based.
-
B.
usedAt
Indicates that something is employed, applied, or utilized at a particular place, time, or context.
-
C.
typeOfSite
chosen
Indicates the specific category or kind of site that an entity is classified as.
-
D.
containsSite
Indicates that one entity spatially or structurally includes another entity as a site or location within its bounds.
-
E.
siteTypeServed
Indicates the type of site or location that is served, supported, or handled by a given entity or resource.
- 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_69a4932941d08190815efd422f0b4ca7 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4991c524481908b2bb88c4feabec6 |
completed | March 1, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69a494bc1f8c8190904356f3a8e801de |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.