Triple
T20022998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epistolario |
E494907
|
entity |
| Predicate | documentsActivityOf |
P82572
|
FINISHED |
| Object | Coluccio Salutati as chancellor of Florence |
—
|
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: Coluccio Salutati as chancellor of Florence | Statement: [Epistolario, documentsActivityOf, Coluccio Salutati as chancellor of Florence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentsActivityOf Context triple: [Epistolario, documentsActivityOf, Coluccio Salutati as chancellor of Florence]
-
A.
documentsActivity
chosen
Indicates that one entity records, describes, or provides evidence of an activity performed by another entity.
-
B.
documentsNow
Indicates that an entity is currently documenting, recording, or writing about another entity at the present time.
-
C.
documentList
Indicates a relationship where one entity serves as a list or collection of documents associated with another entity.
-
D.
documentsCommunity
Indicates that an entity records, describes, or provides information about a particular community.
-
E.
documentsJourneyTo
Indicates that one entity records or describes the travel, route, or progression of another entity from one place or state to another.
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6628a1ecc8190bf6ee0bedb61e0b8 |
completed | April 20, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69e54ce752748190a0a1ffddd0372271 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:35 p.m.