Triple
T26221087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German minority in Poland |
E655764
|
entity |
| Predicate | someMembersHold |
P153407
|
FINISHED |
| Object | German citizenship |
—
|
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: German citizenship | Statement: [German minority in Poland, someMembersHold, German citizenship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: someMembersHold Context triple: [German minority in Poland, someMembersHold, German citizenship]
-
A.
heldByMembersOf
Indicates that something is possessed, controlled, or owned collectively by the members of a specified group or organization.
-
B.
hasMembersWith
chosen
Indicates that a group or collection includes one or more specific members that satisfy a given condition or characteristic.
-
C.
someMembersLater
Indicates that at least some members of a group or set occur, appear, or hold a property at a later time relative to another reference point or group.
-
D.
hasMembers
Indicates that a group, organization, or collection includes certain entities as its members.
-
E.
manyMembersAre
Indicates that a large number of members within a group possess a specified property or participate in a particular role or condition.
- 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_69ee5b4a77e08190bfcb5f8ecdc55abd |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60d4f66748190819e060ab3dc492c |
completed | May 2, 2026, 2:42 p.m. |
| PD | Predicate disambiguation | batch_69f5b007ec1c819092e2c3605933f60b |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:56 p.m.