Triple
T35749218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boos |
E1033270
|
entity |
| Predicate | châteauDeBoosDate |
P176972
|
FINISHED |
| Object | eighteenth century |
—
|
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: eighteenth century | Statement: [Boos, châteauDeBoosDate, eighteenth century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: châteauDeBoosDate Context triple: [Boos, châteauDeBoosDate, eighteenth century]
-
A.
châteauConstructionCentury
chosen
Indicates the century during which a château was constructed.
-
B.
associatedWithChâteau
Indicates a relationship in which an entity is linked or connected to a particular château, such as by ownership, location, origin, or other relevant association.
-
C.
includesChâteau
Indicates that one entity contains, comprises, or features a château as part of its composition, membership, or contents.
-
D.
Château de TriganceInstanceOf
Indicates that Château de Trigance is classified as a specific instance of a broader category or type.
-
E.
rebuiltAsRenaissanceChâteau
Indicates that something was reconstructed or transformed into a Renaissance-style château, replacing or significantly altering its previous form.
- 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_69f76e119d508190a3873cb302063832 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a1961d7c819087a12d0f71be150f |
completed | May 3, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.