Triple
T30545392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Noormarkku |
E777398
|
entity |
| Predicate | hasManorArea |
P200806
|
FINISHED |
| Object | Noormarkku Works manor area |
—
|
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: Noormarkku Works manor area | Statement: [Noormarkku, hasManorArea, Noormarkku Works manor area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasManorArea Context triple: [Noormarkku, hasManorArea, Noormarkku Works manor area]
-
A.
hasManorHouse
Indicates that one entity possesses or is associated with a manor house as a property or feature.
-
B.
hasResidentialArea
Indicates that an entity includes, contains, or is associated with an area designated for people to live or reside.
-
C.
hasManagementArea
Indicates that one entity is responsible for managing, overseeing, or administering a specified area or region.
-
D.
hasFamilyArea
Indicates a relationship where an entity possesses or includes a designated area intended for family use or family-related activities.
-
E.
hasCadastralArea
Indicates that an entity possesses or is associated with a specific cadastral (official land registry) area measurement.
- F. None of above. chosen
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_69f2249d183c8190b79937c1768d2163 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69ffada24d188190a576a02dc280a7fb |
completed | May 9, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69ffad46d6ac819081772f408b1389d5 |
completed | May 9, 2026, 9:55 p.m. |
| PDg | Predicate description generation | batch_69ffada149748190916bfd9b87356342 |
completed | May 9, 2026, 9:56 p.m. |
Created at: April 29, 2026, 8:19 p.m.