Triple
T11556170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philip Fabricius |
E274022
|
entity |
| Predicate | wasThrownFrom |
P100296
|
FINISHED |
| Object | window of Prague Castle |
—
|
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: window of Prague Castle | Statement: [Philip Fabricius, wasThrownFrom, window of Prague Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasThrownFrom Context triple: [Philip Fabricius, wasThrownFrom, window of Prague Castle]
-
A.
throws
Indicates that one entity propels or hurls another entity or object through space, typically by a deliberate physical action.
-
B.
triggeredFrom
Indicates that one event, action, or process was initiated or caused as a result of another specific event, action, or process.
-
C.
leakedFrom
Indicates that information, material, or content has been disclosed or escaped from a particular source, typically without authorization.
-
D.
wasSuppressedBy
Indicates that an action, event, or expression was actively prevented, restrained, or silenced by another agent or force.
-
E.
firedBy
Indicates that one entity has dismissed or terminated another entity from a position, role, or employment.
- F. None of above. chosen
Provenance (4 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88a86be308190973fea5d7db8ba9d |
completed | April 10, 2026, 5:28 a.m. |
| PD | Predicate disambiguation | batch_69d85dc3fc2c8190bed7e2111301a77c |
completed | April 10, 2026, 2:17 a.m. |
| PDg | Predicate description generation | batch_69d87f2e67108190ac36bf47aac12fa8 |
completed | April 10, 2026, 4:40 a.m. |
Created at: April 8, 2026, 9:37 p.m.