Triple
T5524700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hôtel de Soubise |
E144893
|
entity |
| Predicate | integratedIntoStateArchives |
P10288
|
FINISHED |
| Object | early 19th 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: early 19th century | Statement: [Hôtel de Soubise, integratedIntoStateArchives, early 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: integratedIntoStateArchives Context triple: [Hôtel de Soubise, integratedIntoStateArchives, early 19th century]
-
A.
archivesStatus
Indicates the current archival state or condition assigned to an item, such as whether it is archived, active, or pending archiving.
-
B.
archivesHeldIn
chosen
Indicates that archival materials or records are stored, maintained, or preserved at a specified location or institution.
-
C.
integratedIn
Indicates that one entity is incorporated as a component or part within a larger system, structure, or context represented by another entity.
-
D.
convertedStatesInto
Indicates that one entity transformed or changed the status or condition of another entity into a different specified state.
-
E.
archivesModel
Indicates that one entity stores and preserves another entity as an archived model for long-term reference or retrieval.
- 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_69c008f873a481909b4d9f7e2db3c37d |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f874bd081909cccfc25767ee6fa |
completed | March 22, 2026, 4:57 p.m. |
| PD | Predicate disambiguation | batch_69c01b0a06348190b39ac9fe80d2836a |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:34 p.m.