Triple
T30181490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swiss Vice-Consul in Budapest |
E767211
|
entity |
| Predicate | safeHouseFunction |
P36367
|
FINISHED |
| Object | shelter for Jews |
—
|
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: shelter for Jews | Statement: [Swiss Vice-Consul in Budapest, safeHouseFunction, shelter for Jews]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: safeHouseFunction Context triple: [Swiss Vice-Consul in Budapest, safeHouseFunction, shelter for Jews]
-
A.
safetyFunction
chosen
Indicates that one entity serves as a safety-related function or mechanism that protects, safeguards, or reduces risk for another entity or process.
-
B.
houseFunction
Indicates the functional role or primary use that a house serves (e.g., residential, commercial, mixed-use).
-
C.
safeguard
Indicates taking protective actions to shield someone or something from harm, loss, or danger.
-
D.
failsSafeTo
Indicates that one entity does not successfully ensure the safety or protection of another entity or context.
-
E.
protectedGround
Indicates that one entity has taken action to safeguard or defend another entity or area from harm, damage, or unauthorized interference.
- 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_69f2247cc3d88190811dec3face94bf5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f419e088190ba19a6ab9465d951 |
completed | May 2, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:26 p.m.