Triple
T34946831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lansdowne collection |
E1007876
|
entity |
| Predicate | hasPrimaryRegionOfOriginOfWorks |
P193134
|
FINISHED |
| Object | Italy |
E863
|
NE 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: Italy | Statement: [Lansdowne collection, hasPrimaryRegionOfOriginOfWorks, Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryRegionOfOriginOfWorks Context triple: [Lansdowne collection, hasPrimaryRegionOfOriginOfWorks, Italy]
-
A.
authorPrimaryCountryOfActivity
Indicates the main country in which an author predominantly conducts or conducted their professional or creative activities.
-
B.
workOriginatesFrom
Indicates that the creation, development, or initiation of a work can be traced back to a particular source, agent, or origin.
-
C.
hasWorksLocatedIn
Indicates that the works or creations associated with an entity are situated or stored in a specified location.
-
D.
appearsInWorkCountryOfOrigin
Indicates that an entity appears in a work whose country of origin is the specified country.
-
E.
administrativeRegionOfOrigin
chosen
Indicates the administrative region (such as a state, province, or similar division) from which an entity originates or is associated by origin.
- F. None of above.
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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a03446ec72881909c5ff25a48baadb3 |
completed | May 12, 2026, 3:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37a89cb9b881909708b536ee827bae |
completed | June 21, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_6a03439b393c819084aa9b7ed0d5b6b0 |
completed | May 12, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4 p.m.