Triple
T12802537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen’s Bedroom |
E306056
|
entity |
| Predicate | mayBePreservedAs |
P89806
|
FINISHED |
| Object | museum room |
—
|
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: museum room | Statement: [Queen’s Bedroom, mayBePreservedAs, museum room]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBePreservedAs Context triple: [Queen’s Bedroom, mayBePreservedAs, museum room]
-
A.
somePreservedAs
chosen
Indicates that at least one part or instance of an entity is kept or maintained in a particular state, form, or condition.
-
B.
partlyPreservedAs
Indicates that an entity is only partially preserved or remains in incomplete form within another entity or context.
-
C.
hasPreservationType
Indicates the specific method or category of preservation applied to an entity (e.g., how it is stored, conserved, or kept intact).
-
D.
betterPreservedThan
Indicates that one entity is in a superior state of preservation or condition compared to another entity.
-
E.
mayFailToBeConservedIf
Indicates that something which is normally conserved might not remain conserved when a specified condition or circumstance holds.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e7e3be48190ba9159c9f1ac2ccd |
completed | April 10, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69d9640ed7448190b276e7fab649f7d2 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:30 p.m.