Triple
T4771958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German presidential election, 1925 |
E105947
|
entity |
| Predicate | winnerBackground |
P58700
|
FINISHED |
| Object | World War I field marshal |
—
|
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: World War I field marshal | Statement: [German presidential election, 1925, winnerBackground, World War I field marshal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerBackground Context triple: [German presidential election, 1925, winnerBackground, World War I field marshal]
-
A.
winnerMake
Indicates that one entity causes or brings about another entity becoming the winner in a contest, competition, or selection process.
-
B.
winnerLayout
Indicates that one entity is designated as the winning or primary arrangement, configuration, or layout among alternatives.
-
C.
winnerState
Indicates the state or condition of an entity that has achieved victory or been declared the winner in a given context.
-
D.
winnerTitle
Indicates the formal title or designation awarded to the entity that wins a particular competition, contest, or event.
-
E.
winnerRight
Indicates that the referenced entity is the winner on the right side or right position in a competitive or comparative context.
- 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_69bd43f226fc8190b867cc249c2a9042 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd655e5dcc8190a932be9b1baaffb2 |
completed | March 20, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69bd6229d8448190a271719e5e30fd82 |
completed | March 20, 2026, 3:05 p.m. |
| PDg | Predicate description generation | batch_69bd6508e218819086a36236cfa4a249 |
completed | March 20, 2026, 3:17 p.m. |
Created at: March 20, 2026, 1:21 p.m.