Triple
T36912118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raudten |
E912935
|
entity |
| Predicate | hasAdministrativeRoleHistorically |
P29914
|
FINISHED |
| Object | local administrative center |
—
|
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: local administrative center | Statement: [Raudten, hasAdministrativeRoleHistorically, local administrative center]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdministrativeRoleHistorically Context triple: [Raudten, hasAdministrativeRoleHistorically, local administrative center]
-
A.
hasHistoricalRoleAs
chosen
Indicates that an entity has served in a specific historical capacity, function, or position during a particular period or context.
-
B.
hasAdministrativeStatusSince
Indicates that an entity has held a particular administrative status continuously from a specified point in time onward.
-
C.
mayHavePriorRole
Indicates that an entity is allowed or expected to have held a specified role at some earlier time.
-
D.
hasHistoricalActor
Indicates that an entity is associated with or involves a specific historical person as a participant or subject.
-
E.
hasFormerStaffMember
Indicates that an entity once had a person as a staff member, but that person is no longer employed there.
- 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_69f76e879768819085c2fb31a6a5b44b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: May 3, 2026, 4:13 p.m.