Triple
T17452884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Capital of Culture 2015 |
E424956
|
entity |
| Predicate | roleOfTitleHolder |
P22451
|
FINISHED |
| Object | host city |
—
|
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: host city | Statement: [European Capital of Culture 2015, roleOfTitleHolder, host city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfTitleHolder Context triple: [European Capital of Culture 2015, roleOfTitleHolder, host city]
-
A.
titleHolderIs
Indicates that one entity currently holds or possesses a specific title associated with another entity.
-
B.
addressedPersonHoldsTitle
Indicates that the person being addressed holds or possesses a particular title or formal designation.
-
C.
titleHolderCouldBe
Indicates that a particular entity is a possible or potential holder of a specified title or position.
-
D.
titleHolderIsUsually
Indicates that an entity serving as a title holder is typically or most commonly a particular type or category of entity.
-
E.
titleHolderType
chosen
Indicates the specific role or capacity in which an entity holds a title (e.g., owner, trustee, beneficiary).
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4513faa0c8190961cf504c459bf34 |
completed | April 19, 2026, 3:51 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f0e3fc819094e466b74622c956 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:47 a.m.