Triple
T31550201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamminiemi, Helsinki |
E804976
|
entity |
| Predicate | usedAsOfficialResidenceBy |
P6777
|
FINISHED |
| Object | Urho Kekkonen |
—
|
NE NERFINISHED |
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: Urho Kekkonen | Statement: [Tamminiemi, Helsinki, usedAsOfficialResidenceBy, Urho Kekkonen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsOfficialResidenceBy Context triple: [Tamminiemi, Helsinki, usedAsOfficialResidenceBy, Urho Kekkonen]
-
A.
usedAtResidence
Indicates that an object, resource, or service is utilized within or for the purposes of a particular residence.
-
B.
usedAsOfficialResidenceSince
Indicates that an entity has served as the formally designated official residence of another entity starting from a specified point in time.
-
C.
servedAsResidenceOf
chosen
Indicates that something functioned as the home or dwelling place of a particular person or group.
-
D.
usedAsResidenceAgainBy
Indicates that something previously used as a residence is once more being used as a residence by a particular entity.
-
E.
residenceUsedFor
Indicates that a particular residence is used for a specific purpose, function, or activity.
- 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_69f348d11a048190a65eb8384a3754ac |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd6f9d600c8190acf495b7fc632e4b |
completed | May 8, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69fd6e98a2948190a9f78c415ad23b8c |
completed | May 8, 2026, 5:03 a.m. |
Created at: April 30, 2026, 10:10 p.m.