Triple
T14417097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of Wally |
E357480
|
entity |
| Predicate | seizedDuring |
P5949
|
FINISHED |
| Object | Nazi era in Austria |
—
|
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: Nazi era in Austria | Statement: [Portrait of Wally, seizedDuring, Nazi era in Austria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seizedDuring Context triple: [Portrait of Wally, seizedDuring, Nazi era in Austria]
-
A.
seizedCapital
Indicates that one entity forcibly took control of another entity’s capital city.
-
B.
wasDetainedDuring
Indicates that an entity was held in custody or confinement for some period of time during a specified event or time interval.
-
C.
seizedPowerAfter
Indicates that one entity took control or authority from another entity following a specified event or point in time.
-
D.
seizedPowerBy
Indicates that one entity took control or authority from another, typically through force, coercion, or other non-consensual means.
-
E.
confiscatedBy
chosen
Indicates that something has been taken away and seized by an authority or agent, typically as a legal or disciplinary action.
- 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_69d82793421c8190861eb0e673b085de |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de90cec8e4819087c72d82f9caacda |
completed | April 14, 2026, 7:09 p.m. |
| PD | Predicate disambiguation | batch_69de5c30467881908e770e3940295641 |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:17 a.m.